Order payment method and device, storage medium and electronic device

Through the pre-trained voice recognition model, analyzing voice commands in the user's shopping process, generating and confirming orders, solving the problem of unable to place orders and pay during voice shopping, realizing a complete voice interaction in the shopping process, and improving the user experience.

CN119067671APending Publication Date: 2024-12-03QINGDAO HAIER TECH +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411094307.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

When users interact with the application online through voice, the shopping process can only continue until the recommended product is recommended, and subsequent placing and payment processes based on voice cannot be carried out.

Method used

The pre-trained voice recognition model is adopted to generate and resolve orders through user voice commands, including target product selection, delivery address input and payment confirmation, to achieve a complete voice interaction in the shopping process.

Benefits of technology

It solves the problem of not being able to place subsequent orders and payments during voice shopping, improves the flexibility of user experience and video data transmission, and realizes a complete voice interaction in the shopping process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067671A_ABST
    Figure CN119067671A_ABST
Patent Text Reader

Abstract

The invention discloses an order payment method and device, a storage medium and an electronic device, and relates to the technical field of smart home, and the order payment method comprises the steps: displaying a recommended commodity list determined through a first model to a user according to the shopping intention of the user, the first model is a pre-trained model for recognizing voice sent by a user in a complete shopping process; the received first voice of the user is analyzed according to the first model to generate an order for a target commodity, and the first voice is used for indicating the target commodity selected by the user from the recommended commodity list; the received second voice of the user is analyzed through the first model so as to assist the user in outputting the virtual resources corresponding to the order, and the second voice is used for indicating and confirming the output of the virtual resources.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and more specifically, to a payment method and device for an order, a storage medium, and an electronic device. Background Art

[0002] In the related art, there is a solution that allows users to perform voice shopping through smart speakers. However, the smart speakers in this solution cannot be carried around, the application location is fixed, and the user experience is poor. Furthermore, in the related art, there is also a solution for voice shopping through mobile applications (Application, referred to as APP), which specifically converts the user's voice into text, and then uses artificial intelligence generated content (Artificial Intelligence Generated Content, referred to as AIGC) technology to display the products in the form of pictures and texts. However, this solution only goes as far as recommending products to users, and it is impossible to conduct subsequent orders and payments with users based on voice.

[0003] Regarding the related technology, when users interact with applications through voice to shop online, the voice-based shopping process can only last until the recommendation of products, and subsequent ordering and payment processes cannot be performed based on voice. No effective solution has been proposed yet.

[0004] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0005] The embodiments of the present application provide a payment method and device for an order, a storage medium, and an electronic device, so as to at least solve the problem in the related art that when a user interacts with an application through voice to shop online, the voice-based shopping process can only continue to the point of recommending products, and subsequent ordering and payment processes cannot be performed based on voice.

[0006] According to one aspect of an embodiment of the present application, a payment method for an order is provided, comprising: displaying a list of recommended products determined by a first model to a user based on the user's shopping intention, wherein the first model is a model pre-trained to recognize voices uttered by the user in a complete shopping process; parsing a first voice of the user received according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the list of recommended products; parsing a second voice of the user received through the first model to assist the user in outputting virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

[0007] In an exemplary embodiment, a list of recommended products determined by a first model is displayed to a user based on the user's shopping intention, including: receiving a third voice emitted by the user, wherein the third voice is used to indicate that the user needs to shop; parsing the third voice to obtain the shopping intention of the user; calling a product search engine associated with the first model according to the shopping intention to obtain the recommended product list; and displaying the recommended product list to the user.

[0008] In an exemplary embodiment, the first voice received from the user is parsed according to the first model to generate an order for a target product, including: parsing the first voice through the first model to obtain the target product; broadcasting the product information of the target product to the user through a fourth voice; and generating an order for the target product upon receiving a fifth voice from the user, wherein the fifth voice is the user's feedback voice to the fourth voice, and the fifth voice is used to instruct the user to confirm the purchase of the target product.

[0009] In an exemplary embodiment, generating an order for the target product includes: parsing the sixth voice of the user received according to the first model to obtain the first delivery address of the user, wherein the sixth voice is issued after the fifth voice and is used to indicate the delivery address of the user; and generating the order according to the first delivery address.

[0010] In an exemplary embodiment, generating the order according to the first delivery address includes: broadcasting the first delivery address to the user through a seventh voice; receiving an eighth voice from the user based on feedback from the seventh voice; and upon confirming through the first model that the eighth voice indicates that the first delivery address is accurate, calling the transaction system through the first delivery address to generate the order.

[0011] In an exemplary embodiment, after receiving the eighth voice from the user based on the seventh voice feedback, the method further includes: upon confirming through the first model that the eighth voice indicates that the first delivery address is inaccurate, parsing the second delivery address from the ninth voice, wherein the ninth voice includes at least one of the following: the eighth voice, the tenth voice issued by the user within the target time interval after issuing the eighth voice; upon confirming with the user that the second delivery address is accurate, calling the transaction system through the second delivery address to generate the order.

[0012] In an exemplary embodiment, before displaying the recommended product list determined by the first model to the user according to the user's shopping intention, the method further includes: obtaining historical voices uttered by different users in the complete shopping process; performing data cleaning on the historical voices to obtain cleaned voices; and iteratively training the second model through the cleaned voices to obtain the first model. The second model is an untrained speech recognition model.

[0013] According to another aspect of an embodiment of the present application, a payment device for an order is also provided, including: a display module, used to display a list of recommended products determined by a first model to a user according to the user's shopping intention, wherein the first model is a model pre-trained to recognize the voice uttered by the user in a complete shopping process; a first parsing module, used to parse the first voice of the user received according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the list of recommended products; a second parsing module, used to parse the second voice of the user received through the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

[0014] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the payment method of the above order when running.

[0015] According to another aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the payment method for the order through the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the payment method for the above order is implemented.

[0017] Through this application, a list of recommended products determined by a first model is displayed to a user according to the user's shopping intention, wherein the first model is a model that is pre-trained to recognize the voice issued by the user in the complete shopping process; the first voice of the user received is parsed according to the first model to generate an order for the target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list; the second voice of the user received is parsed by the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources. That is to say, in the user's complete shopping process, at least the first voice, the second voice, etc. parsed by the first model are used to generate an order for the target product that the user needs to purchase, and the virtual resources corresponding to the order are output. Therefore, the above technical solution is adopted to solve the problem in the related technology that when the user interacts with the application through voice to conduct online shopping, the voice-based shopping process can only continue to the recommended product, and the subsequent ordering and payment processes cannot be performed based on voice; and the flexibility of video data transmission is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 It is a schematic diagram of the hardware environment of an optional order payment method according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of an optional order payment method according to an embodiment of the present application;

[0022] Figure 3 is a training flow chart of a model according to an embodiment of the present application;

[0023] Figure 4 is another flow chart of an optional order payment method according to an embodiment of the present application;

[0024] Figure 5 This is a structural block diagram of an optional order payment device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to one aspect of the embodiment of the present application, a payment method for an order is provided. The payment method for the order is widely used in smart home (Smart Home), smart home, smart home device ecology, smart house (IntelligenceHouse) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the payment method for the order can be applied to Figure 1 In the hardware environment shown in FIG. 1 , a plurality of terminal devices 102 and a server 104 are formed. Figure 1 As shown, the server 104 is connected to multiple terminal devices 102 via a network, and can be used to provide services (such as application services, etc.) for the terminals or clients installed on the terminals. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0028] The 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: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0029] In this embodiment, a payment method for an order is provided, including but not limited to being applied to an application program. Figure 2 : is a flow chart of a payment method for an order according to an embodiment of the present application, and the flow includes the following steps:

[0030] Step S202: displaying a list of recommended products determined by a first model to the user according to the user's shopping intention, wherein the first model is a model pre-trained to recognize speech uttered by the user in a complete shopping process;

[0031] Optionally, the first model may be integrated into any application for shopping, and the application may be installed on various types of mobile terminals.

[0032] Step S204: parsing the received first voice of the user according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list;

[0033] Step S206: parsing the second voice of the user received through the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

[0034] Through the above steps, the recommended commodity list determined by the first model is displayed to the user according to the user's shopping intention, wherein the first model is a model that is pre-trained to recognize the voice issued by the user in the complete shopping process; the first voice of the user received is parsed according to the first model to generate an order for the target commodity, wherein the first voice is used to indicate the target commodity selected by the user from the recommended commodity list; the second voice of the user received is parsed by the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources. That is to say, in the complete shopping process of the user, at least the first voice, the second voice, etc. parsed by the first model are used to generate an order for the target commodity that the user needs to purchase, and the virtual resources corresponding to the order are output. Therefore, the above technical solution solves the problem in the related art that when the user interacts with the application through voice to conduct online shopping, the voice-based shopping process can only continue to the recommended commodity, and the subsequent ordering and payment processes cannot be performed based on voice; and the flexibility of video data transmission is improved.

[0035] In an exemplary embodiment, a list of recommended products determined by a first model is displayed to a user based on the user's shopping intention, including: receiving a third voice emitted by the user, wherein the third voice is used to indicate that the user needs to shop; parsing the third voice to obtain the shopping intention of the user; calling a product search engine associated with the first model according to the shopping intention to obtain the recommended product list; and displaying the recommended product list to the user.

[0036] The embodiment of the present application analyzes the user's third voice and obtains the shopping intention. Then, the product search engine associated with the first model is called to obtain all products that meet the user's shopping intention. A recommended product list is generated based on the basic information of all products that meet the user's shopping intention and displayed to the user. The basic information includes: text information describing the product and image information of the product. Optionally, displaying the recommended product list to the user includes: displaying the basic information to the user through an interactive interface for interacting with the user, and broadcasting the text information in the basic information to the user in sequence.

[0037] In an exemplary embodiment, the first voice received from the user is parsed according to the first model to generate an order for a target product, including: parsing the first voice through the first model to obtain the target product; broadcasting the product information of the target product to the user through a fourth voice; and generating an order for the target product upon receiving a fifth voice from the user, wherein the fifth voice is the user's feedback voice to the fourth voice, and the fifth voice is used to instruct the user to confirm the purchase of the target product.

[0038] After parsing the first voice to obtain the target product, the product information of the target product is broadcast to the user through the fourth voice to confirm that the user really needs to purchase the target product. Optionally, the product information can be basic information of the target product or keywords used to describe the target product. When the user confirms to purchase the target product through the fifth voice, an order for the target product is generated.

[0039] Optionally, generating an order for the target product includes: parsing the sixth voice of the user received according to the first model to obtain the first delivery address of the user, wherein the sixth voice is issued after the fifth voice and is used to indicate the delivery address of the user; and generating the order according to the first delivery address. That is, the sixth voice of the user is parsed by the first model, and the order is generated according to the obtained first delivery address.

[0040] Furthermore, generating the order according to the first delivery address includes: broadcasting the first delivery address to the user through a seventh voice; receiving an eighth voice from the user based on feedback from the seventh voice; and upon confirming through the first model that the eighth voice indicates that the first delivery address is accurate, calling the transaction system through the first delivery address to generate the order.

[0041] In the process of generating an order through the first delivery address, the application program in which the first model is located will broadcast the first delivery address obtained by parsing the first model to the user through the seventh voice to determine whether the first parsing result of the first model (i.e., the first delivery address) is accurate. If the user indicates through the eighth voice that the first parsing result of the first model is accurate, the order can be generated through the first delivery address.

[0042] Furthermore, after receiving the eighth voice from the user based on the seventh voice feedback, the method also includes: when it is confirmed through the first model that the eighth voice indicates that the first delivery address is inaccurate, parsing the second delivery address from the ninth voice, wherein the ninth voice includes at least one of the following: the eighth voice, and the tenth voice issued by the user within the target time interval after issuing the eighth voice; when it is confirmed with the user that the second delivery address is accurate, calling the transaction system through the second delivery address to generate the order.

[0043] If the user indicates through the eighth voice that the first delivery address is inaccurate, the eighth voice can be parsed again through the first model to obtain a second parsing result, or the tenth voice uttered by the user within the target time interval after uttering the eighth voice can be parsed through the first model to obtain a third parsing result.

[0044] If the second analysis result is consistent with the third analysis result, the third analysis result or the second analysis result is voice broadcasted to the user for judgment;

[0045] In the case where the second analysis result is inconsistent with the third analysis result, if it is determined that both the second analysis result and the third analysis result are inconsistent with the first analysis result, the second analysis result and the third analysis result are both voice broadcasted to the user for judgment; if it is determined that any one of the second analysis result and the third analysis result is inconsistent with the first analysis result, the other of the second analysis result and the third analysis result is voice broadcasted to the user for judgment. The eighth voice analysis and the broadcasting of the analysis result are repeated until the user confirms the second delivery address.

[0046] It should be noted that, in order to improve the user experience, the address determination times can be set. If the number of times the target resolution result is broadcasted to the user reaches the address determination times, a prompt voice is broadcasted to prompt the user to manually fill in the address. The target resolution result includes: the first resolution result, the second resolution result, and the third resolution result.

[0047] It should also be noted that the target analysis result can be displayed on the interactive interface between the application and the user at the same time as being announced by voice.

[0048] In an exemplary embodiment, before displaying the recommended product list determined by the first model to the user according to the user's shopping intention, the method further includes: obtaining historical voices uttered by different users in the complete shopping process; performing data cleaning on the historical voices to obtain cleaned voices; and iteratively training the second model through the cleaned voices to obtain the first model. The second model is an untrained speech recognition model.

[0049] It is understandable that if Figure 3 As shown, the training process of the second model includes the following steps:

[0050] Step S301: prepare industry data, that is, prepare various voice commands (equivalent to historical voice) issued by users in the complete shopping process recorded in the industry.

[0051] Step S302: Data cleaning, that is, cleaning the historical speech data.

[0052] Step S303: feature engineering, i.e. performing feature engineering processing on the cleaned speech to obtain a data set.

[0053] Feature Engineering is a technique in the field of data processing and machine learning. Its main purpose is to extract, construct, and select useful features (i.e., input variables) from raw data in order to more effectively represent data during modeling and prediction. Feature engineering is essential to improving the accuracy and performance of models.

[0054] Feature engineering includes the following aspects:

[0055] 1. Data cleaning: remove noise, errors and duplicate data from the data set to ensure data consistency and reliability.

[0056] 2. Data transformation: Converting raw data into a form suitable for analysis, for example, converting non-numerical data into numerical data, or converting time series data into a form suitable for a specific model.

[0057] 3. Feature extraction: Extract useful information from raw data, such as extracting keywords from text data, or extracting edge and texture features from image data.

[0058] 4. Feature construction: Create new features by combining, transforming, or generating new variables, for example, by calculating statistics (mean, median, standard deviation, etc.) in the data set or by applying mathematical and logical operations (such as addition, subtraction, multiplication, division, etc.) to construct new features.

[0059] 5. Feature selection: Select the most useful features for model prediction from a large number of features to reduce the complexity of the model and the risk of overfitting. Feature selection methods include filtering methods (such as correlation coefficient, chi-square test, etc.), packaging methods (such as recursive feature elimination, feature importance, etc.) and embedding methods (such as model-based feature selection).

[0060] 6. Feature scaling: Adjust the scale of features so that they are in the same range so that the model will not be affected by scale differences when processing different features. Common feature scaling methods include standardization (Z-score standardization) and normalization (min-max normalization).

[0061] Feature engineering is a critical step in machine learning projects. By effectively processing and selecting features, the performance and generalization ability of the model can be significantly improved.

[0062] Step S304: basic large model selection, that is, selecting the second model, the second model may be, for example, the AIGC large model.

[0063] Step S305: divide the data set into a training set and a validation set.

[0064] Step S306: fine-tune the model; or, fine-tune the model based on the evaluation results.

[0065] Step S307: training the second model using the training set.

[0066] Step S308: Evaluate the trained second model using the validation set to obtain an evaluation result.

[0067] Step S309: Determine whether the trained second model meets expectations through the evaluation results; if so, execute step S309; ​​if not, execute step S306 to fine-tune the model through the evaluation results.

[0068] Step S310: output the proprietary model, that is, determine the trained second model as the first model and output the first model.

[0069] Obviously, the above-described embodiments are only a part of the embodiments of the present application, not all of the embodiments. In order to better understand the payment method of the above-mentioned order, the above-mentioned process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application, specifically:

[0070] The optional embodiments of the present application are based on a multimodal large model and search recommendation technology, and implement product recommendations through voice interaction between the APP and the user until the transaction is completed and payment is made. It is suitable for the complete shopping process of the user, and is used to improve the user's purchase process experience and add a new online product purchase interaction method.

[0071] Specifically, in the optional embodiments of the present application, speech recognition and natural language processing technologies are used to understand the user's intention, convert it into search keywords, call the product search engine, obtain the search recommended products, and recommend the products to the user through voice and text. The user can specify detailed information about the specific product through language interaction, and can also place an order and pay through language instructions. The payment verification can be confirmed by face recognition or voice recognition.

[0072] Specifically, Figure 4 As shown, the interaction process between the user and the APP in the optional embodiment of the present application includes:

[0073] Step S401: The user speaks a voice to wake up the voice service.

[0074] Step S402: Send a voice reply on the interactive interface to indicate that you are ready.

[0075] Step S403: The user says what he wants to buy.

[0076] Step S404: calling the proprietary model service to perform speech recognition and analysis.

[0077] Step S405: Return the identified keywords.

[0078] Step S406: calling the product search service.

[0079] Step S407: Return to the recommended product list.

[0080] Step S408: Display and announce the recommended products on the interactive interface.

[0081] Step S409: the user voice (ie, the third voice) selects a product (ie, the target product) and places an order.

[0082] Step S410: calling a proprietary model service to perform speech recognition and analysis.

[0083] Step S411: Return the product key.

[0084] Step S412: Call the order interface.

[0085] Step S413: Return to the product order confirmation page.

[0086] Step S414: a confirmation page is displayed, and a voice (i.e., the fourth voice) announces the product, prompting the purchaser to confirm the purchase.

[0087] Step S415: The user voice (ie, the sixth voice) says that the delivery address is xxx.

[0088] Step S416: Call the proprietary model service to perform speech recognition and analysis.

[0089] Step S417: Return the address code and address details (equivalent to the first delivery address).

[0090] Step S418: Call the interface for modifying the delivery address.

[0091] Step S419: Modify the delivery address and update the confirmation page.

[0092] Step S420: The page displays and announces the delivery address.

[0093] Step S421: The user confirms the order by voice.

[0094] Step S422: Call the proprietary model service to perform speech recognition and analysis.

[0095] Step S423: Confirm the order instruction.

[0096] Step S424: Confirm the generated order.

[0097] Step S425: The order is successfully placed and the payment interface is called up.

[0098] Step S426: The page displays and announces that the order is successful, please pay.

[0099] Step S427: The user voice (ie, the second voice) says to confirm the payment.

[0100] Step S428: Call the proprietary model service to perform speech recognition and analysis.

[0101] Step S429: Confirm the payment instruction.

[0102] Step S430: Confirm payment.

[0103] Step S431: Payment is successful and returns to the success interface.

[0104] Step S432: The page displays and announces the payment success and the payment amount.

[0105] In an optional embodiment of the present application, during the product search and recommendation process, voice interaction can be repeated to obtain more ideal products through more accurate expression of user needs.

[0106] In summary, the optional embodiment of the present application integrates a multimodal large model (i.e., the first model) on the mobile terminal, which is suitable for the entire mobile shopping process, transforms the existing product search and transaction process, makes product recommendations more in line with expectations, and improves the user's shopping experience during the shopping process.

[0107] Through the description of the above implementation methods, 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 by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0108] In this embodiment, a payment device for an order is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0109] Figure 5 : is a structural block diagram of an optional order payment device according to an embodiment of the present application, the device comprising:

[0110] A display module 52, configured to display to the user a list of recommended products determined by a first model according to the user's shopping intention, wherein the first model is a model pre-trained to recognize speech emitted by the user in a complete shopping process;

[0111] A first parsing module 54 is configured to parse the first voice of the user received according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list;

[0112] The second parsing module 56 is used to parse the second voice of the user received through the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

[0113] Through the above device, a list of recommended products determined by a first model is displayed to the user according to the user's shopping intention, wherein the first model is a model that is pre-trained to recognize the voice issued by the user in the complete shopping process; the first voice of the user received is parsed according to the first model to generate an order for the target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list; the second voice of the user received is parsed by the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources. That is to say, in the complete shopping process of the user, at least the first voice, the second voice, etc. parsed by the first model are used to generate an order for the target product that the user needs to purchase, and the virtual resources corresponding to the order are output. Therefore, the above technical solution solves the problem in the related art that when the user interacts with the application through voice to conduct online shopping, the voice-based shopping process can only continue to the recommended product, and the subsequent ordering and payment processes cannot be performed based on voice; and the flexibility of video data transmission is improved.

[0114] In an exemplary embodiment, the display module 52 is used to: receive a third voice emitted by the user, wherein the third voice is used to indicate that the user needs to shop; parse the third voice to obtain the shopping intention of the user; call the product search engine associated with the first model according to the shopping intention to obtain the recommended product list; and display the recommended product list to the user.

[0115] In an exemplary embodiment, the first parsing module 54 is used to: parse the first voice through the first model to obtain the target product; broadcast the product information of the target product to the user through the fourth voice; and generate an order for the target product when receiving the fifth voice of the user, wherein the fifth voice is the user's feedback voice to the fourth voice, and the fifth voice is used to instruct the user to confirm the purchase of the target product.

[0116] In an exemplary embodiment, the first parsing module 54 is used to: parse the sixth voice of the user received according to the first model to obtain the first delivery address of the user, wherein the sixth voice is issued after the fifth voice and is used to indicate the delivery address of the user; generate the order according to the first delivery address.

[0117] In an exemplary embodiment, the first parsing module 54 is used to: announce the first delivery address to the user through a seventh voice; receive an eighth voice feedback from the user based on the seventh voice; and, upon confirming through the first model that the eighth voice indicates that the first delivery address is accurate, call the transaction system through the first delivery address to generate the order.

[0118] In an exemplary embodiment, the first parsing module 54 is used to: parse the second delivery address from the ninth voice when it is confirmed through the first model that the eighth voice indicates that the first delivery address is inaccurate, wherein the ninth voice includes at least one of the following: the eighth voice, and the tenth voice issued by the user within the target time interval after issuing the eighth voice; and call the transaction system to generate the order through the second delivery address when it is confirmed with the user that the second delivery address is accurate.

[0119] In an exemplary embodiment, the device further includes a training module, which is used to: obtain historical voices uttered by different users in the complete shopping process; perform data cleaning on the historical voices to obtain cleaned voices; and iteratively train the second model using the cleaned voices to obtain the first model. The second model is an untrained speech recognition model.

[0120] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0121] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0122] S1, displaying a list of recommended products determined by a first model to the user according to the user's shopping intention, wherein the first model is a model pre-trained to recognize the speech uttered by the user in the complete shopping process;

[0123] S2, parsing the first voice of the user received according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list;

[0124] S3, parsing the second voice of the user received through the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

[0125] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0126] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0127] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0128] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0129] S1, displaying a list of recommended products determined by a first model to the user according to the user's shopping intention, wherein the first model is a model pre-trained to recognize the speech uttered by the user in the complete shopping process;

[0130] S2, parsing the first voice of the user received according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list;

[0131] S3, parsing the second voice of the user received through the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

[0132] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0133] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0134] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0135] An embodiment of the present application also provides a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the above method embodiments.

[0136] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0137] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0138] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A payment method for an order, It is characterized in that include: Displaying a list of recommended products determined by a first model to the user according to the user's shopping intention, wherein the first model is a model pre-trained to recognize speech uttered by the user in a complete shopping process; parsing the received first voice of the user according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list; The second voice of the user received is parsed through the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

2. A payment method for an order according to claim 1, It is characterized in that The recommended product list determined by the first model is displayed to the user according to the user's shopping intention, including: receiving a third voice message from the user, wherein the third voice message is used to indicate that the user needs to shop; parsing the third voice to obtain the shopping intention of the user; Invoking a product search engine associated with the first model according to the shopping intention to obtain the recommended product list; The recommended product list is displayed to the user.

3. A payment method for an order according to claim 1, It is characterized in that Parsing the received first speech of the user according to the first model to generate an order for a target product includes: Parsing the first speech by using the first model to obtain the target product; announcing the product information of the target product to the user through a fourth voice; When a fifth voice of the user is received, an order for the target product is generated, wherein the fifth voice is a feedback voice of the user to the fourth voice, and the fifth voice is used to instruct the user to confirm the purchase of the target product.

4. A payment method for an order according to claim 3, It is characterized in that Generating an order for the target product, including: Parsing the received sixth voice of the user according to the first model to obtain the first delivery address of the user, wherein the sixth voice is issued after the fifth voice and is used to indicate the delivery address of the user; The order is generated according to the first delivery address.

5. A payment method for an order according to claim 4, It is characterized in that Generating the order according to the first delivery address includes: announcing the first delivery address to the user through a seventh voice; receiving an eighth voice feedback from the user based on the seventh voice; When it is confirmed through the first model that the first delivery address indicated by the eighth voice is accurate, the transaction system is called through the first delivery address to generate the order.

6. A payment method for an order according to claim 5, It is characterized in that After receiving an eighth voice fed back by the user based on the seventh voice, the method further includes: When it is confirmed through the first model that the eighth voice indicates that the first delivery address is inaccurate, a second delivery address is parsed from a ninth voice, wherein the ninth voice includes at least one of the following: the eighth voice, a tenth voice uttered by the user within a target time interval after uttering the eighth voice; After confirming with the user that the second delivery address is accurate, the transaction system is called through the second delivery address to generate the order.

7. A payment method for an order according to claim 1, It is characterized in that Before presenting the recommended product list determined by the first model to the user according to the user's shopping intention, the method further includes: Obtain historical voice messages from different users during the entire shopping process; Performing data cleaning on the historical speech to obtain cleaned speech; The second model is iteratively trained using the cleaned speech to obtain the first model, wherein the second model is an untrained speech recognition model.

8. A payment device for an order, It is characterized in that include: A display module, configured to display to the user a list of recommended products determined by a first model according to the user's shopping intention, wherein the first model is a model pre-trained to recognize speech uttered by the user in a complete shopping process; a first parsing module, configured to parse the received first voice of the user according to the first model to generate an order for a target product, wherein the first voice is used to indicate the target product selected by the user from the recommended product list; The second parsing module is used to parse the second voice of the user received through the first model to assist the user in outputting the virtual resources corresponding to the order, wherein the second voice is used to indicate confirmation of outputting the virtual resources.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, It is characterized in that A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.