CN114864047A - Recipe recommendation method, storage medium and electronic device - Google Patents

Abstract

The present application discloses a recipe recommendation method, a storage medium and an electronic device, and relates to the technical field of smart home/smart home. The recipe recommendation method includes: acquiring audio to be recognized; when semantic features of the audio to be recognized meet recipe recommendation conditions , obtain the voiceprint feature of the audio to be recognized, wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized, and the voiceprint feature is the feature of the voiceprint information corresponding to the audio to be recognized; The sound source object; when the object attribute of the sound source object is obtained, obtain the first recipe information according to the object attribute of the sound source object; when the object attribute of the sound source object is not obtained, obtain the second recipe information. By adopting the above technical solution, the technical problem that the specified user cannot be accurately recommended due to the generalized recommended recipe for the user is solved.

Description

Recipe recommendation method, storage medium and electronic device

technical field

The present application relates to the field of communications, and in particular, to a recipe recommendation method, a storage medium, and an electronic device.

Background technique

At present, many applications have the function of recommending recipes for users, and users can choose from the recommended recipes.

However, when an application recommends recipes to users, it is usually generalized and cannot make precise recommendations for specific users.

In the related art, due to the generalized recommended recipes for users, there is no effective solution to the technical problem that an accurate recommendation cannot be made for a specified user.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a recipe recommendation method, a storage medium, and an electronic device to at least solve the technical problem in the related art that an accurate recommendation cannot be made for a specified user due to a generalized recommended recipe for a user.

According to an embodiment of the present invention, a recipe recommendation method is provided, including: acquiring audio to be recognized; and acquiring a voiceprint feature of the audio to be recognized when the semantic feature of the audio to be recognized satisfies a recipe recommendation condition , wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized, the voiceprint feature is the feature of the voiceprint information corresponding to the audio to be recognized; the sound source object associated with the audio to be recognized is determined according to the voiceprint feature In the case of acquiring the object attribute of the above-mentioned sound source object, obtain first recipe information according to the object attribute of the above-mentioned sound source object, wherein the above-mentioned first recipe information is the matching degree with the object attribute of the above-mentioned sound source object Recipe information that reaches a preset threshold; in the case that the object attribute of the sound source object is not acquired, acquire second recipe information, wherein the second recipe information is preset basic recipe information.

In an exemplary embodiment, determining the sound source object associated with the audio to be identified according to the voiceprint feature includes one of the following: sending the voiceprint feature to a third-party server, and using the first target in the third-party server The algorithm processes the voiceprint feature, and after obtaining the sound source object associated with the audio to be identified, receiving the sound source object associated with the audio to be identified returned by the third-party server; using the locally stored second target algorithm to process the voiceprint feature, Obtain the sound source object associated with the audio to be identified.

In an exemplary embodiment, using the locally stored second target algorithm to process the voiceprint feature to obtain the sound source object associated with the audio to be identified includes: performing dimension reduction processing on the voiceprint feature; using a clustering algorithm Obtain the sound source object associated with the audio to be identified.

In an exemplary embodiment, the obtaining the first recipe information according to the object attribute of the sound source object when the object attribute of the sound source object is obtained includes: storing information related to the sound source object in the database. In the case of a linked fixed recipe, obtain the recipe information of the above fixed recipe.

In an exemplary embodiment, the obtaining the first recipe information according to the object attribute of the sound source object when the object attribute of the sound source object is obtained includes: not storing a database related to the sound source object In the case of a linked fixed recipe, according to the object attribute of the sound source object stored in the database, the recipe information whose matching degree with the object attribute of the sound source object reaches a preset threshold is obtained.

In an exemplary embodiment, the obtaining the second recipe information without obtaining the object attribute of the sound source object includes: obtaining the pre-recipe information under the condition that the relevant information of the sound source object is not stored in the database. basic recipe information.

In an exemplary embodiment, in the case that the relevant information of the sound source object is not stored in the database, obtaining the preset basic recipe information includes: in the case that the relevant information of the sound source object is not stored in the database , determining the role to which the sound source object belongs according to the voiceprint feature; and acquiring basic recipe information matching the role to which the sound source object belongs according to the role to which the sound source object belongs.

According to another embodiment of the embodiments of the present invention, a recipe recommendation apparatus is further provided, including: a first acquisition module, configured to acquire the audio to be recognized; and a second acquisition module, configured to satisfy the above-mentioned semantic features of the audio to be recognized In the case of recipe recommendation conditions, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized, and the voiceprint feature is the feature of the voiceprint information corresponding to the audio to be recognized. A determination module is used to determine the sound source object associated with the audio to be identified according to the above-mentioned voiceprint feature; the third acquisition module is used to obtain the object attribute of the above-mentioned sound source object according to the above-mentioned sound source object. Attribute acquisition first recipe information, wherein the above-mentioned first recipe information is recipe information whose matching degree with the object attribute of the above-mentioned sound source object reaches a preset threshold; in the case where the object attribute of the above-mentioned sound source object is not obtained , and obtain second recipe information, where the above-mentioned second recipe information is preset basic recipe information.

According to another aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, where a computer program is stored in the computer-readable storage medium, wherein the computer program is configured to execute the above recipe recommendation method when running .

According to another aspect of the embodiments of the present invention, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above recipe through the computer program recommended method.

In the embodiment of the present invention, the audio to be recognized is acquired; if the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, the voiceprint feature of the audio to be recognized is acquired, wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized , the voiceprint feature is the feature of the voiceprint information corresponding to the audio to be identified; the sound source object associated with the audio to be identified is determined according to the voiceprint feature; when the object attribute of the sound source object is obtained, according to the object attribute of the sound source object Obtain the first recipe information, wherein the first recipe information is the recipe information whose matching degree with the object attribute of the sound source object reaches a preset threshold; if the object attribute of the sound source object is not obtained, obtain the second recipe information. Recipe information, wherein the second recipe information is preset basic recipe information. By adopting the above technical solution, by acquiring the voiceprint feature of the sound source object, determining the sound source object according to the voiceprint feature, and recommending a matching recipe to the sound source object, it is possible to accurately recommend the recipe to the specified user, and solve the problem of solving the problem. Due to the generalized recommended recipes for users, there is a technical problem that an accurate recommendation cannot be made for a specified user.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application.

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. In other words, on the premise of no creative labor, other drawings can also be obtained from these drawings.

1 is a schematic diagram of an application scenario of an optional recipe recommendation method according to an embodiment of the present application;

2 is a flowchart of an optional recipe recommendation method according to an embodiment of the present invention;

3 is a schematic diagram of an optional recipe recommendation method according to an embodiment of the present invention;

4 is a schematic diagram of another optional recipe recommendation method according to an embodiment of the present invention;

FIG. 5 is a structural block diagram of an optional recipe recommendation apparatus according to an embodiment of the present invention.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only The embodiments are part of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the scope of protection of the present application.

It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

According to an aspect of the embodiments of the present application, a recipe recommendation method is provided. The recipe recommendation method is widely used in whole-house intelligent digital control application scenarios such as smart home, smart home, smart home device ecology, and smart house ecology. Optionally, in this embodiment, the above recipe recommendation method may be applied to the hardware environment formed by the terminal device 102 and the server 104 as shown in FIG. 1 . As shown in FIG. 1 , the server 104 is connected to the terminal device 102 through the network, and can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal, and a database can be set on the server or independent of the server for To provide the server 104 with data storage services, cloud computing and/or edge computing services may be configured on the server or independently of the server for providing the server 104 with data computing services.

The above network may include, but is not limited to, at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: a wide area network, a metropolitan area network, and a local area network, and the wireless network may include but not limited to at least one of the following: WIFI (Wireless Fidelity, wireless fidelity), Bluetooth. The terminal device 102 may not be limited to PCs, mobile phones, tablet computers, smart air conditioners, smart hoods, smart refrigerators, smart ovens, smart stoves, smart washing machines, smart water heaters, smart washing devices, smart dishwashers, and smart projection devices. , Smart TV, Smart Clothes Rack, Smart Curtain, Smart Video, Smart Socket, Smart Audio, Smart Speaker, Smart Fresh Air Equipment, Smart Kitchen and Bathroom Equipment, Smart Bathroom Equipment, Smart Sweeping Robot, Smart Window Cleaning Robot, Smart Mopping Robot, Smart air purification equipment, smart steamer, smart microwave oven, smart kitchen treasure, smart purifier, smart water dispenser, smart door lock, etc.

A recipe recommendation method is provided in this embodiment, and FIG. 2 is a flowchart of the recipe recommendation method according to an embodiment of the present invention, and the process includes the following steps:

Step S202, acquiring the audio to be recognized;

Step S204, in the case that the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized, and the voiceprint feature is the corresponding feature of the audio to be recognized. characteristics of the voiceprint information;

Step S206, determining the sound source object associated with the audio to be identified according to the voiceprint feature;

Step S208, in the case of obtaining the object attribute of the sound source object, obtain first recipe information according to the object attribute of the sound source object, wherein the first recipe information is that the matching degree with the object attribute of the sound source object reaches a predetermined level. Recipe information with a threshold value is set; in the case that the object attribute of the sound source object is not obtained, second recipe information is obtained, wherein the second recipe information is preset basic recipe information.

Optionally, in this embodiment, the device for acquiring audio may include, but is not limited to, various devices with speech recognition functions, such as smart refrigerators, smart air conditioners, and smart washing machines, which are not limited here; the audio to be recognized may include but not limited to Not limited to the various types of sounds made by humans, animals, wind, machines, etc.

Optionally, in this embodiment, the semantic features of the audio to be recognized that satisfy the recipe recommendation conditions may include, but are not limited to, the semantic features are related to eating; acquiring the voiceprint features of the audio to be recognized may include, but is not limited to, using a third-party server or local Stored algorithms to identify the voiceprint features of audio.

Optionally, in this embodiment, the sound source object may include, but is not limited to, a user identifier and personal attribute information of the user. For example, the database stores the correspondence between user IDs and voiceprint features, and the correspondence between personal attribute information and voiceprint features, where personal attribute information may include, but is not limited to, gender, height, weight, and dietary preferences.

Optionally, in this embodiment, the food whose matching degree with the object attribute of the sound source object reaches a preset threshold may include, but is not limited to, a fixed recipe related to the sound source object, and recipe information before the sound source object. Associated recipes, recipes associated with the role to which the sound source object belongs; methods for displaying recipe information matching the sound source object include at least one or more of the following methods: the method of displaying text information on the device screen, the method of voice broadcast The method and the method of sending the short message to the device associated with the sound source object are not limited here.

Acquire the audio to be recognized through the solution provided by the embodiment of the present application; in the case that the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the semantic content corresponding to the audio to be recognized The voiceprint feature is the feature of the voiceprint information corresponding to the audio to be identified; the sound source object associated with the audio to be identified is determined according to the voiceprint feature; when the object attribute of the sound source object is obtained, according to the sound source object The object attribute obtains first recipe information, wherein the first recipe information is the recipe information whose matching degree with the object attribute of the sound source object reaches a preset threshold; in the case where the object attribute of the sound source object is not obtained, obtain The second recipe information, wherein the second recipe information is preset basic recipe information. By adopting the above technical solution, by acquiring the voiceprint feature of the sound source object, determining the sound source object according to the voiceprint feature, and recommending a matching recipe to the sound source object, it is possible to accurately recommend the recipe to the specified user, and solve the problem of solving the problem. Due to the generalized recommended recipes for users, there is a technical problem that an accurate recommendation cannot be made for a specified user.

In an exemplary embodiment, determining the sound source object associated with the audio to be identified according to the voiceprint feature includes one of the following: sending the voiceprint feature to a third-party server, where the third-party server uses a first target algorithm to process the voiceprint feature , after obtaining the sound source object associated with the audio to be identified, receive the sound source object associated with the audio to be identified returned by the third-party server; use the locally stored second target algorithm to process the voiceprint feature to obtain the sound source object associated with the audio to be identified.

Optionally, in this embodiment, when the target processing algorithm is not stored locally on the device or the operating pressure of the device exceeds a preset threshold, the voiceprint feature can be sent to a third-party server, and the third-party server uses the voiceprint to identify the algorithm. The algorithm identifies the sound source object associated with the audio to be identified, which is not limited here; if the target processing algorithm is stored locally on the device and the operating pressure of the device does not exceed the preset threshold, the voiceprint recognition algorithm stored locally on the device can be used to identify The sound source object associated with the audio to be identified is not limited here.

With the solution provided by the embodiment of the present application, the sound source object associated with the audio to be recognized is recognized by the third-party server or the device itself, which improves the flexibility of voiceprint recognition.

In an exemplary embodiment, using a locally stored second target algorithm to process the voiceprint feature to obtain a sound source object associated with the audio to be identified includes: performing dimension reduction processing on the voiceprint feature; using a clustering algorithm to obtain the audio to be identified The associated sound source object.

Optionally, in this embodiment, when using the voiceprint recognition algorithm stored locally on the device to identify the sound source object associated with the audio to be identified, the voiceprint feature of the sound source object can be obtained through the interaction record associated with the sound source object, And through dimensionality reduction, clustering algorithm for integration, and locate the centroid range of the sound source object to identify.

With the solution provided by the embodiment of the present application, the sound source object associated with the audio to be identified is identified through a dimensionality reduction and clustering algorithm, which improves the accuracy of identification.

In an exemplary embodiment, when the object attribute of the sound source object is obtained, obtaining the first recipe information according to the object attribute of the sound source object includes: storing a fixed recipe associated with the sound source object in the database , get the recipe information of the fixed recipe.

Optionally, in this embodiment, in the case where a fixed recipe associated with the sound source object is stored in the database, for example, the database has pre-stored recipe information of the sound source object for nearly a week or a month, you can Get recipe information associated with today's date based on today's date. As shown in Fig. 3, the database stores the recipe information of the sound source object for the past week. If today is Tuesday, the recipe information obtained by the device is "Meal B".

With the solution provided by the embodiments of the present application, in the case where a fixed recipe associated with the sound source object is stored in the database, a fixed recipe matching the sound source object is obtained, which achieves the effect of accurately recommending a recipe for a specified user.

In an exemplary embodiment, when the object attribute of the sound source object is obtained, obtaining the first recipe information according to the object attribute of the sound source object includes: not storing a fixed recipe associated with the sound source object in the database In the case of , according to the object attribute of the sound source object stored in the database, the recipe information whose matching degree with the object attribute of the sound source object reaches a preset threshold is obtained.

Optionally, in this embodiment, the object attributes of the sound source object may include, but are not limited to, a user ID, gender, height, weight, and dietary preferences; in the case where the previous recipe information associated with the user ID is stored in the database In this case, the recipes associated with the previous recipe information can be recommended to the sound source object; if the object attribute information is information such as gender, height, weight, diet preference, etc., the sound source object can be recommended to the sound source object according to the gender, Recipes for height, weight, dietary preferences, and more.

With the solution provided by the embodiment of the present application, by acquiring recipe information matching the object attribute of the sound source object, the accuracy of recommending recipes to a designated user is improved.

In an exemplary embodiment, obtaining the second recipe information without obtaining the object attribute of the sound source object includes: obtaining a preset basis under the condition that the relevant information of the sound source object is not stored in the database Recipe information.

Optionally, in this embodiment, in the case where the relevant information of the sound source object is not stored in the database, basic recipe information may be recommended to the sound source object, wherein the basic recipe information may include, but is not limited to, a relatively high degree of user acceptance. , recipes that are loved by most users, such as scrambled eggs with tomatoes.

With the solution provided by the embodiments of the present application, in the case where the relevant information of the sound source object is not stored in the database, the preset basic recipe information is obviously obtained, which improves the accuracy of recommending recipes to a designated user.

In an exemplary embodiment, in the case that the relevant information of the sound source object is not stored in the database, acquiring the preset basic recipe information includes: in the case that the relevant information of the sound source object is not stored in the database, according to the sound source object The pattern feature determines the role to which the sound source object belongs; according to the role to which the sound source object belongs, basic recipe information matching the role to which the sound source object belongs is obtained.

Optionally, in this embodiment, the character to which the sound source object belongs can be determined according to the voiceprint feature, for example, the old man, the middle-aged, the child, etc.; when the character to which the sound source object belongs is determined, the character belonging to the sound source object can be obtained. Basic recipe information for character matching. For example, when the target is an elderly person or a child, a non-spicy or soft recipe can be recommended to the sound source target; when the target is middle-aged, a spicy recipe can be recommended to the sound source target.

With the solution provided by the embodiment of the present application, basic recipe information matching the role to which the sound source object belongs is obtained according to the role to which the sound source object belongs, which improves the accuracy of recommending recipes to a designated user.

In order to better understand the process of the above recipe recommendation method, the above recipe recommendation method is described below with reference to optional embodiments, but is not used to limit the technical solutions of the embodiments of the present invention.

A schematic diagram of a recipe recommendation method is provided in this embodiment, as shown in FIG. 4 .

After the user triggers audios such as "what to eat today, what to eat today", etc., the program will trigger the program to determine which user or the elderly, children, etc. according to the current user's voiceprint characteristics;

After obtaining the voiceprint features, you can directly access the third-party service voiceprint recognition ability, or you can obtain the voiceprint features through the user's usual interaction records, then reduce the dimension, integrate the clustering algorithm, and locate the current user's centroid range to obtain;

The program will actively query the recommended recipes (this recipe will be dynamically maintained), if not, it will actively query the basic recipes, and after the user selects the recipes he needs, it will automatically add the recipes to the user-defined recommended recipes to form a closed loop;

During the interaction process, it will take the initiative to carry out humanized interaction with users, such as; "Recommend tomato scrambled eggs for you, practice..."

In business processing, caching will be done based on redis, such as user information, to improve response time.

The architecture used in the embodiment of the present invention is as follows:

1) Spring Boot

Spring Boot is a new framework provided by the Pivotal team, designed to simplify the initial setup and development of new Spring applications. The framework uses a specific way to configure, so that developers no longer need to define boilerplate configuration. In this way, Spring Boot aims to be a leader in the burgeoning field of rapid application development.

2) redis cache

redis is a high-performance key-value database. Supports data persistence, supports multiple data structures, and supports data backup. It can reduce the pressure on the database, improve the overall performance, and bring a better user experience.

3) Nacos

nacos is a service infrastructure for building modern application architectures centered on "services" (such as microservices paradigm, cloud native paradigm), dedicated to the discovery, management and information configuration of microservices, and can help developers quickly realize dynamic service discovery, Service configuration, service metadata and traffic management for more agile and easier building, delivery and management of microservice platforms. nacos supports the discovery, configuration and management of almost all mainstream types of services (such as: Kubernetes Service, gRPC&Dubbo RPC Service, SpringCloud RESTful Service).

4) websocket

Websocket is a protocol for full-duplex communication over a single TCP connection, making data exchange between the client and server simpler, allowing the server to actively push data to the client. In the websocket API, the browser and the server only need to complete a handshake once, and a persistent connection can be created directly between the two, and two-way data transmission can be performed.

From the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products are stored in a storage medium (such as ROM/RAM, magnetic disk, CD-ROM), including several instructions to make a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present invention.

FIG. 5 is a structural block diagram of a recipe recommendation device according to an embodiment of the present invention; as shown in FIG. 5 , it includes:

The first acquisition module 501 is used to acquire the audio to be recognized;

The second acquisition module 502 is configured to acquire the voiceprint feature of the audio to be recognized when the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized, and the voiceprint feature is the feature of the voiceprint information corresponding to the audio to be recognized;

A determination module 503, configured to determine the sound source object associated with the audio to be identified according to the voiceprint feature;

The third obtaining module 504 is configured to obtain first recipe information according to the object attribute of the sound source object when the object attribute of the sound source object is obtained, wherein the first recipe information is between the object attribute of the sound source object and the sound source object. Recipe information whose matching degree reaches a preset threshold; when the object attribute of the sound source object is not acquired, acquire second recipe information, where the second recipe information is preset basic recipe information.

Acquire the audio to be recognized through the solution provided by the embodiment of the present application; in the case that the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the semantic content corresponding to the audio to be recognized The voiceprint feature is the feature of the voiceprint information corresponding to the audio to be identified; the sound source object associated with the audio to be identified is determined according to the voiceprint feature; when the object attribute of the sound source object is obtained, according to the sound source object The object attribute obtains first recipe information, wherein the first recipe information is the recipe information whose matching degree with the object attribute of the sound source object reaches a preset threshold; in the case where the object attribute of the sound source object is not obtained, obtain The second recipe information, wherein the second recipe information is preset basic recipe information. By adopting the above technical solution, by acquiring the voiceprint feature of the sound source object, determining the sound source object according to the voiceprint feature, and recommending a matching recipe to the sound source object, it is possible to accurately recommend the recipe to the specified user, and solve the problem of solving the problem. Due to the generalized recommended recipes for users, there is a technical problem that an accurate recommendation cannot be made for a specified user.

An embodiment of the present invention further provides a storage medium, where the storage medium includes a stored program, wherein the above-mentioned program executes any one of the above-mentioned methods when running.

Optionally, in this embodiment, the above-mentioned storage medium may be configured to store program codes for executing the following steps:

S1, obtain the audio to be recognized;

S2, in the case that the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized, and the voiceprint feature is the feature corresponding to the audio to be recognized Characteristics of voiceprint information;

S3, determine the sound source object associated with the audio to be identified according to the voiceprint feature;

S4, in the case of obtaining the object attribute of the sound source object, obtain first recipe information according to the object attribute of the sound source object, wherein the first recipe information is that the matching degree with the object attribute of the sound source object reaches a preset level Recipe information of a threshold; in the case where the object attribute of the sound source object is not acquired, acquire second recipe information, where the second recipe information is preset basic recipe information.

Acquire the audio to be recognized through the solution provided by the embodiment of the present application; in the case that the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the semantic content corresponding to the audio to be recognized The voiceprint feature is the feature of the voiceprint information corresponding to the audio to be identified; the sound source object associated with the audio to be identified is determined according to the voiceprint feature; when the object attribute of the sound source object is obtained, according to the sound source object The object attribute obtains first recipe information, wherein the first recipe information is the recipe information whose matching degree with the object attribute of the sound source object reaches a preset threshold; in the case where the object attribute of the sound source object is not obtained, obtain The second recipe information, wherein the second recipe information is preset basic recipe information. By adopting the above technical solution, by acquiring the voiceprint feature of the sound source object, determining the sound source object according to the voiceprint feature, and recommending a matching recipe to the sound source object, it is possible to accurately recommend the recipe to the specified user, and solve the problem of solving the problem. Due to the generalized recommended recipes for users, there is a technical problem that an accurate recommendation cannot be made for a specified user.

An embodiment of the present invention also provides an electronic device, comprising a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any of the above method embodiments.

Optionally, the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.

Optionally, in this embodiment, the above-mentioned processor may be configured to execute the following steps through a computer program:

S1, obtain the audio to be recognized;

S2, in the case that the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the feature of the semantic content corresponding to the audio to be recognized, and the voiceprint feature is the feature corresponding to the audio to be recognized Characteristics of voiceprint information;

S3, determine the sound source object associated with the audio to be identified according to the voiceprint feature;

S4, in the case of obtaining the object attribute of the sound source object, obtain first recipe information according to the object attribute of the sound source object, wherein the first recipe information is that the matching degree with the object attribute of the sound source object reaches a preset level Recipe information of a threshold; in the case where the object attribute of the sound source object is not acquired, acquire second recipe information, where the second recipe information is preset basic recipe information.

Acquire the audio to be recognized through the solution provided by the embodiment of the present application; in the case that the semantic feature of the audio to be recognized satisfies the recipe recommendation condition, acquire the voiceprint feature of the audio to be recognized, wherein the semantic feature is the semantic content corresponding to the audio to be recognized The voiceprint feature is the feature of the voiceprint information corresponding to the audio to be identified; the sound source object associated with the audio to be identified is determined according to the voiceprint feature; when the object attribute of the sound source object is obtained, according to the sound source object The object attribute obtains first recipe information, wherein the first recipe information is the recipe information whose matching degree with the object attribute of the sound source object reaches a preset threshold; in the case where the object attribute of the sound source object is not obtained, obtain The second recipe information, wherein the second recipe information is preset basic recipe information. By adopting the above technical solution, by acquiring the voiceprint feature of the sound source object, determining the sound source object according to the voiceprint feature, and recommending a matching recipe to the sound source object, it is possible to accurately recommend the recipe to the specified user, and solve the problem of solving the problem. Due to the generalized recommended recipes for users, there is a technical problem that an accurate recommendation cannot be made for a specified user.

Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (Read-Only Memory, referred to as ROM), a random access memory (Random Access Memory, referred to as RAM), Various media that can store program codes, such as removable hard disks, magnetic disks, or optical disks.

Optionally, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and optional implementation manners, and details are not described herein again in this embodiment.

Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device, which can be centralized on a single computing device, or distributed in a network composed of multiple computing devices Alternatively, they may be implemented in program code executable by a computing device, such that they may be stored in a storage device and executed by the computing device, and in some cases, in a different order than here The steps shown or described are performed either by fabricating them separately into individual integrated circuit modules, or by fabricating multiple modules or steps of them into a single integrated circuit module. As such, the present invention is not limited to any particular combination of hardware and software.

The above are only the preferred embodiments of the present application. It should be pointed out that for those skilled in the art, without departing from the principles of the present application, several improvements and modifications can also be made. It should be regarded as the protection scope of this application.

Claims (10)

1. A recipe recommendation method comprising:

acquiring audio to be identified;

acquiring a voiceprint feature of the audio to be recognized under the condition that the semantic feature of the audio to be recognized meets a recipe recommendation condition, wherein the semantic feature is the feature of semantic content corresponding to the audio to be recognized, and the voiceprint feature is the feature of voiceprint information corresponding to the audio to be recognized;

determining a sound source object associated with the audio to be identified according to the voiceprint features;

under the condition that the object attribute of the sound source object is obtained, obtaining first recipe information according to the object attribute of the sound source object, wherein the first recipe information is the recipe information of which the matching degree with the object attribute of the sound source object reaches a preset threshold value;

and under the condition that the object attribute of the sound source object is not acquired, acquiring second recipe information, wherein the second recipe information is preset basic recipe information.

2. The method according to claim 1, wherein the determining the sound source object associated with the audio to be identified according to the voiceprint feature comprises one of:

sending the voiceprint features to a third-party server, and receiving the sound source object associated with the audio to be identified, which is returned by the third-party server, after the third-party server processes the voiceprint features by using a first target algorithm to obtain the sound source object associated with the audio to be identified;

and processing the voiceprint characteristics by using a second target algorithm stored locally to obtain a sound source object associated with the audio to be identified.

3. The method according to claim 2, wherein the processing the voiceprint features by using a second target algorithm stored locally to obtain a sound source object associated with the audio to be identified comprises:

performing dimension reduction processing on the voiceprint features;

and obtaining the sound source object associated with the audio to be identified by utilizing a clustering algorithm.

4. The method according to claim 1, wherein the acquiring first recipe information according to the object attribute of the sound source object in the case of acquiring the object attribute of the sound source object includes:

and acquiring recipe information of the fixed recipe when the fixed recipe associated with the sound source object is stored in a database.

5. The method according to claim 1, wherein the acquiring first recipe information according to the object attribute of the sound source object in the case of acquiring the object attribute of the sound source object includes:

and under the condition that a fixed recipe related to the sound source object is not stored in a database, acquiring recipe information of which the matching degree with the object attribute of the sound source object reaches a preset threshold value according to the object attribute of the sound source object stored in the database.

6. The method of claim 1, wherein the obtaining second recipe information without obtaining the object properties of the sound source object comprises:

and under the condition that the related information of the sound source object is not stored in the database, acquiring preset basic recipe information.

7. The method according to claim 6, wherein the obtaining of the preset basic recipe information in case that the related information of the sound source object is not stored in the database comprises:

under the condition that the related information of the sound source object is not stored in a database, determining the role to which the sound source object belongs according to the voiceprint characteristics;

and acquiring basic recipe information matched with the role to which the sound source object belongs according to the role to which the sound source object belongs.

8. A recipe recommendation device, comprising:

the first acquisition module is used for acquiring the audio to be identified;

the second acquisition module is used for acquiring the voiceprint characteristics of the audio to be recognized under the condition that the semantic characteristics of the audio to be recognized meet the recipe recommendation condition, wherein the semantic characteristics are the characteristics of semantic contents corresponding to the audio to be recognized, and the voiceprint characteristics are the characteristics of voiceprint information corresponding to the audio to be recognized;

the determining module is used for determining the sound source object related to the audio to be identified according to the voiceprint characteristics;

a third obtaining module, configured to obtain first recipe information according to an object attribute of the sound source object when the object attribute of the sound source object is obtained, where the first recipe information is recipe information in which a matching degree with the object attribute of the sound source object reaches a preset threshold; and under the condition that the object attribute of the sound source object is not acquired, acquiring second recipe information, wherein the second recipe information is preset basic recipe information.

9. A computer-readable storage medium, comprising a stored program, wherein the program when executed performs the method of any of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 7 by means of the computer program.

Images