WO2020232616A1

WO2020232616A1 - Information recommendation method and apparatus, and electronic device and storage medium

Info

Publication number: WO2020232616A1
Application number: PCT/CN2019/087666
Authority: WO
Inventors: 郭子亮
Original assignee: 深圳市欢太科技有限公司; Oppo广东移动通信有限公司
Priority date: 2019-05-20
Filing date: 2019-05-20
Publication date: 2020-11-26
Also published as: CN113330475A

Abstract

Disclosed are an information recommendation method and apparatus, and an electronic device and a storage medium. The method comprises: a voice assistant starting to receive voice information after being started; after the voice information is received, identifying the received voice information; when it is identified that the received voice information comprises take-out related information, acquiring target take-out merchant information to be recommended, wherein the target take-out merchant information is take-out merchant information matching a user portrait of a user bound with the voice assistant; and displaying a card, and displaying the target take-out merchant information in the card. By means of the method, a user can trigger the display of take-out related information by means of speech, and a voice assistant can recommend matching take-out merchant information to the user according to a user portrait, such that the user can more quickly acquire a take-out commodity required thereby, thereby greatly improving the user experience.

Description

Information recommendation method, device, electronic equipment and storage medium

Technical field

This application relates to the field of Internet of Things, and more specifically, to an information recommendation method, device, electronic equipment, and storage medium.

Background technique

With the development of voice recognition technology, more electronic devices are equipped with voice assistants to interact with users of electronic devices. In the process of interacting with voice assistants, users can use voice assistants to complete some operations. However, related Voice assistants have not yet been involved in the food delivery field.

Summary of the invention

In view of the above problems, this application proposes an information recommendation method, device, electronic equipment, and storage medium to improve the above problems.

In the first aspect, the present application provides an information recommendation method, which is applied to a voice assistant, and the method includes: the voice assistant starts to receive voice information after being started; and when the voice information is received, responding to the received voice Information; if it is recognized that the received voice information includes takeaway-related information, obtain the target takeaway merchant information to be recommended, and the target takeaway merchant information matches the user portrait of the user bound to the voice assistant The takeaway merchant information; display a card, and display the target takeaway merchant information in the card.

In a second aspect, an information recommendation method, the device includes: a voice information receiving unit, configured to receive voice information after the voice information processing device is started; a voice recognition unit, configured to respond to the voice information after receiving the voice information The received voice information is recognized; the takeaway information acquisition unit, if it recognizes that the received voice information includes takeaway related information, obtains the target takeaway merchant information to be recommended, and the target takeaway merchant information is related to the The voice assistant binds the information of the takeaway merchant that matches the user portrait of the user; the information display unit is used to display the card, and displays the target takeaway merchant information in the card.

In a third aspect, this application provides an electronic device including one or more processors and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be The one or more processors execute the above-mentioned methods.

In a fourth aspect, the present application provides a computer-readable storage medium having program code stored in the computer-readable storage medium, wherein the above-mentioned method is executed when the program code is running, and control confusion can also be avoided.

The present application provides an information recommendation method, device, electronic equipment, and storage medium. After the voice assistant starts to receive voice information, when the voice information is received, the received voice information is recognized. When the received voice information includes takeaway related information, the takeaway merchant information matching the user portrait of the user bound to the voice assistant is obtained as the target takeaway merchant information to be recommended, the card is displayed, and the card is displayed The target takeaway merchant information is displayed in. Thus, through this method, the user can trigger the display of takeaway related information through voice, and the voice assistant can recommend matching takeaway merchant information to the user according to the user’s portrait, so that the user can quickly obtain the takeaway goods he needs. Furthermore, there is no need to separately start the target client for ordering food, and then through multiple page scrolling to find the food you need, which greatly improves the user experience.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

Fig. 1 shows a flowchart of a voice information processing method proposed in an embodiment of the present application;

Fig. 2 shows a schematic diagram of a voice information collection interface proposed by an embodiment of the present application;

FIG. 3 shows a schematic diagram of a takeaway voice setting interface proposed in an embodiment of the present application;

FIG. 4 shows a schematic diagram of a result of adding a takeaway voice setting interface according to an embodiment of the present application;

FIG. 5 shows a schematic diagram of a voice assistant communicating with a server of a target takeaway client according to an embodiment of the present application;

Fig. 6 shows a schematic diagram of a card proposed in an embodiment of the present application;

FIG. 7 shows a schematic diagram of a multi-card display proposed in an embodiment of the present application;

FIG. 8 shows a schematic diagram of a card switching proposed in an embodiment of the present application;

FIG. 9 shows a schematic diagram of a card displaying detailed information of a merchant according to an embodiment of the present application;

FIG. 10 shows a flowchart of a voice information processing method proposed by another embodiment of the present application;

FIG. 11 shows a flowchart of a voice information processing method proposed by still another embodiment of this application;

FIG. 12 shows a structural block diagram of a voice information processing device proposed by an embodiment of the present application;

FIG. 13 shows a structural block diagram of a voice information processing device proposed by another embodiment of the present application;

FIG. 14 shows a structural block diagram of a voice information processing device proposed by still another embodiment of the present application;

FIG. 15 shows a structural block diagram of an electronic device of the present application for executing the voice information processing method according to an embodiment of the present application;

Fig. 16 is a storage unit for storing or carrying program codes for implementing the voice information processing method according to the embodiment of the present application.

Detailed ways

The technical solutions 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 a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of this application.

With the development of voice recognition technology, electronic devices such as smart phones, tablets, and computers are equipped with intelligent voice assistants. For example, Apple's Siri, Samsung's Bixby, Google Assistant, Amazon Alex, etc. The voice assistant can be regarded as an intelligent application. The user can help the user solve some practical problems or replace the user in operating the electronic device through the intelligent interaction of the intelligent dialogue with the voice assistant and the instant question and answer.

For example, in a related scenario, when the voice assistant of an electronic device detects that the user input "Help me open Baidu map", the electronic device can recognize that the user's intention is to use the Baidu map application, so that it can start Baidu The map starts. In another related scenario, when the voice assistant of the electronic device detects that the user input "Where is there a parking lot nearby", the electronic device can recognize that the user is looking for a parking lot within a certain range, then the electronic device can be based on the location Search for parking lots and display the search results.

However, the inventor found in his research on voice assistants that the related voice assistants still cannot well recognize the semantics of the takeaway-related information entered by the user, or even if they can respond, they cannot bring the user a better user experience. . For example, in one method, after the relevant voice assistant recognizes the user’s input to order takeaway or takeaway, it either uses "order takeaway" or "takeaway" as keywords to search for resources in a similar manner to a search engine, and then displays the searched The textual information of, or it may be directly searched for nearby restaurants for display. However, the inventor found that the response of the related voice assistant to the food-related information is not the real intention of the user, and thus cannot improve the user's experience and cannot meet the actual needs of the user. Furthermore, the inventor also found that in the process of directly using relevant take-out software to place a take-out order, users need to repeatedly slide the page to find the goods they need, which in turn will also cause a poor user experience.

Therefore, the inventor proposes a voice information processing method, device, electronic device, and storage medium that can improve the above-mentioned problems in this application. Through the method provided by the embodiments of the present application, the user can trigger the display of takeaway related information through voice, and can directly complete the order placement operation in the voice assistant, and there is no need to separately start the target client for ordering takeaway , And then through multiple page swipes to find the takeaway you need, which greatly improves the user experience. Furthermore, this method enables the user to trigger the display of takeaway related information through voice, and the voice assistant can recommend matching takeaway merchant information to the user according to the user's portrait, so that the user can obtain the takeaway goods he needs faster .

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

Please refer to FIG. 1, an information recommendation method provided by an embodiment of the present application is applied to a language assistant, and the method includes:

Step S110: The voice assistant starts to receive voice information after being started.

Among them, it is understandable that the voice assistant may be an application program that runs independently in an electronic device. It can also be a component configured in a certain application. During the user's use, the user can trigger the activation of the voice assistant by touching the physical buttons of the electronic device, or trigger the activation of the voice assistant by touching the virtual buttons displayed on the electronic device.

For example, as a way, when the electronic device is equipped with the HOME button, the electronic device can be configured in advance to trigger the associated target application to start by long pressing the HOME button or double-clicking the HOME button, or long pressing the HOME button or double-clicking the HOME button In the case of triggering a component in the associated target application to start, configure the associated target application or a component in the target application as a voice assistant, so that the voice can be triggered by long pressing the HOME button or double-clicking the HOME button The assistant starts.

As another way, if the electronic device is equipped with a touch screen, the electronic device can be configured with an entrance that triggers the activation of the voice assistant on the desktop of the system or in an application. In the case where the voice assistant portal is configured on the desktop, the portal can be a desktop application icon named as the voice assistant, and when an portal that triggers the voice assistant to start is configured in a certain application, the portal can be a certain A control named Voice Assistant, for example, a text control or a button control.

When the voice assistant is started, the electronic device can display the interface shown in Figure 2. After the interface is displayed, the electronic device will trigger the configured microphone or other physical voice collection components to start sound collection, so that the activated voice The assistant can obtain the collected voice information.

Step S120: After receiving the voice information, recognize the received voice information.

It is understandable that the voice information received by the voice assistant is still a voice signal. The voice assistant also needs to convert the voice information in the form of voice signal into the voice information in text form, and this conversion process is to recognize the received voice information the process of.

In the embodiment of the present application, the voice assistant has multiple ways to realize the recognition of the received voice information.

As a way, the API (Application Programming Interface) of the third-party speech recognition system can be pre-configured. In this way, the voice assistant can wait for the third-party speech recognition system based on the pre-configured API of the third-party speech recognition system. The recognized voice signal is transmitted to a third party for recognition, and then the voice information in text form returned by the third party is received. For example, the API of a third-party speech recognition system provided by Microsoft or Google can be used.

As another way, the neural network model can be trained in advance to obtain a model capable of converting voice information in the form of sound signals into voice information in text form. Then the trained model is deployed in a designated server or service cluster, and the voice assistant can transmit the received voice information in the form of voice signals to the process of recognizing the received voice information. The server or service cluster performs recognition, and then receives the recognized text voice information returned by the server or service cluster.

In another way, the voice assistant can call the API of a third-party speech recognition system for recognition, and transmit it to a designated server or service cluster for recognition and real-time selection, so as to enhance the flexibility of recognition.

In this way, optionally, the voice assistant can determine which form of recognition to perform according to the current network status. It is understandable that the communication process will be more stable when directly connected to the network through the WIFI hotspot than through the mobile communication base station. Then the voice assistant can recognize that the current access to the network is through WIFI, Call the API of the third-party speech recognition system for recognition, and when it is recognized that the mobile communication base station is currently connected to the network, it is transmitted to the designated server or service cluster for recognition.

Furthermore, the voice assistant can also switch the recognition mode based on the recognition success rate. It is understandable that the pronunciation habits or speaking styles of different users will be different, so even for the same recognition method, there will be different recognition results due to the user's own pronunciation habits or speaking styles. Then in this case, the voice assistant can switch the recognition mode according to the user's own habits and combined with the recognition success rate. Among them, the voice assistant can determine that the recognition fails when it detects that the user has repeatedly recognized similar sound signals. Then the voice assistant can switch to another recognition method after recognizing a specified number of failures using a certain recognition method. For example, if the voice assistant starts to use the API of a third-party voice recognition system for recognition, and detects that it has recognized three similar sound signals in a row (the specified number of times is 3), then it is determined to switch to transmission to the server or service Identify in the cluster. It should be noted that similar sound signals can be judged by judging the error energy of the two sound signals.

Step S130: If it is recognized that the received voice information does not include takeaway related information, the current process is ended.

Step S131: If it is recognized that the received voice information includes takeaway related information, obtain the target takeaway merchant information to be recommended, where the target takeaway merchant information matches the user portrait of the user bound to the voice assistant Takeaway merchant information.

Among them, takeaway-related information includes: I want to order takeaway, order takeaway or takeaway.

It is understandable that the voice assistant will only trigger to obtain the information of the takeaway merchants after identifying some specific information, for example, the information of the target takeaway merchants to be recommended. The specific information includes takeaway-related information, which can include "I want to order takeaway", "order takeaway" or "takeaway". Then in this way, when the voice assistant recognizes that the received voice information includes takeaway-related information, it determines that the user wants to order takeaway, and then obtains the target takeaway merchant information to be recommended.

Among them, there are many ways to configure takeaway-related information.

As a way, several common takeaway-related information obtained after statistics can be configured by default when the voice assistant is installed. For example, the aforementioned "I want to order takeaway", "order takeaway" or "takeaway", etc.

Furthermore, as another way, it can also be configured by users according to their own needs. As user needs change, more users expect to adopt a more personalized way to control electronic devices. For example, some users like to say "I want something to eat" or "I'm hungry", etc. Then, in order to make the voice assistant adapt to users with different language expression habits, the user can configure the configuration of takeaway related information.

For example, as shown in FIG. 3, the take-out language setting interface 98 shown in FIG. 3 includes a take-out related information addition control 97 and a display control 96 to which take-out related information has been added. Furthermore, after the user clicks the takeaway related information adding control 97, new takeaway related information can be added. And in the adding process, in addition to adding in the form of text, it can also be added in the form of sound signal at the same time. For example, when the user clicks on the takeaway-related information addition control 97 to trigger the user to enter the takeaway-related information in the form of voice, for example, after the user inputs "I want to eat", in addition to the display control 96 of the takeaway-related information, the text "I After "I want to eat", the sound signal corresponding to "I want to eat" is also stored. In this way, after receiving the voice information, the language assistant can directly compare the received voice signal with the pre-stored voice signal in order to improve the final feedback effect. It is understandable that the voice signal is compared In the signal process, the aforementioned method of comparing the signal similarity can be used to determine whether the received sound signal has a similar match with the pre-stored sound signal. If so, you can directly obtain the takeaway merchant information without further follow-up Language to text conversion recognition.

In the embodiment of this application, the language assistant has multiple ways to obtain the target takeaway merchant information to be recommended.

As a way, the language assistant can obtain the target takeaway merchant information to be recommended based on the data interface with the target takeaway client. In this way, the language assistant will send an information acquisition request to the target takeaway client, and the information acquisition request is used to trigger the target takeaway client to obtain the target takeaway merchant information to be recommended according to a specified rule; and receive the information The target client returns the target takeaway merchant information to be recommended. As shown in Figure 5, in this way, the voice assistant will first use the communication channel 95 to send the information acquisition request to the target takeaway client. The target takeaway client can first query whether there is cached takeaway merchant information locally. Return directly to the voice assistant. If it detects that there is no cached takeaway merchant information, it sends a request for takeaway merchant information to the server based on the communication channel 94, and then returns to the language assistant through the communication channel 94 and the communication channel 95 in turn. It is understandable that the target takeaway client here is a client that can be used to independently generate takeaway orders and place orders. Similar to Meituan Takeaway Client or Ele.me Client.

As another way, sending an information acquisition request to the server corresponding to the target takeaway client, where the information acquisition request is used to trigger the server to obtain the takeaway merchant information according to a specified rule;

Receive the target takeaway merchant information to be recommended returned by the server. For example, please refer to Figure 5 again. In this way, the voice assistant sends an information acquisition request directly to the server through the communication channel 93, and then returns the target takeaway merchant information to be recommended to the voice assistant through the communication channel 93 .

In another way, the language assistant can forward the information acquisition request to the server through the target takeaway client, and the server directly returns the information of the target takeaway merchant to be recommended to the voice assistant without passing through the target takeaway customer. End conversion, and then increase the information transmission rate. It is understandable that, for devices other than the electronic device where the voice assistant is located, the application program is distinguished by the port number occupied by the application program. For example, the browser client occupies port 80 and the voice assistant occupies port 8080. If the returned information points to port 8080, the electronic device will know that this information is returned to the voice assistant. In this way, the voice assistant adds the port number occupied by the voice assistant to the generated information acquisition request, and then when the server generates the returned information, the voice assistant’s port number is added to the returned information so that the information can be Is sent directly to the voice assistant.

It should be noted that the target takeaway merchant information to be recommended in this embodiment may include obtaining the takeaway merchant information of the takeaway merchant closest to the user’s current location based on multiple dimensions, or it may be that the delivery range matches the user and The takeaway merchant information of several takeaway merchants with a high degree of praise may also be the takeaway merchant information of the takeaway merchants that directly adapt to the user's historical order goods, of course, it can also be the takeaway merchant information after the above-mentioned rules are mixed. In this embodiment, the specific specified rule is not specifically limited, and one or more of the foregoing multiple rules may be used in combination. In addition, the specified rules used can also be changed periodically.

Step S140: Display a card, and display the target takeaway merchant information in the card.

After obtaining the target takeaway merchant information to be recommended, the target takeaway merchant information can be displayed in the card 92 as shown in FIG. 6. Among them, the target takeaway merchant information may include the name of the takeaway merchant, scoring information, the starting price of sales, and the type of goods. In addition, you can also directly include some high-volume or characteristic products in the takeaway merchant information.

Of course, as a way, the voice assistant can detect the quantity of the target takeaway merchant information; if it detects that the quantity of the target takeaway merchant information is multiple, multiple cards are displayed, each of which displays one Target takeaway merchant information. For example, as shown in FIG. 7, when three takeaway merchant information are identified, three

cards

92a, 92b, and 92c can be displayed respectively to display the three target takeaway merchant information. In addition, if the number of identified target takeaway merchant information cannot be directly displayed on the same interface, only part of the target takeaway merchant information can be displayed first, and then after detecting that the user swipes toward the upper side of the screen, load more merchant information. Display and hide part of the target takeaway merchant information that has been displayed before. For example, in the interface shown in FIG. 8, after detecting that the user slides the screen in the direction indicated by the arrow, the card 92a ranked closest to the direction indicated by the arrow will be hidden, and a new card 92e will be loaded for display.

It is understandable that, after the step of displaying the card and displaying the target takeaway merchant information in the card, it further includes: obtaining the information of the takeaway merchant to be placed determined from the target takeaway merchant information; The order is generated by describing the information of the takeaway merchant to be placed.

After displaying the target takeaway merchant information, the user can further control, and then the voice assistant can display more information so that the user can select the desired product to place an order.

Among them, as a way, the voice assistant can send the selected target merchant information to the target client after acquiring the target merchant information selected by the user, and the selected target merchant information is used to trigger the target client to generate Order information, and display the generated order information. It is understandable that in this manner, the voice assistant will trigger the target client to switch to the foreground display, and then trigger the target client to generate order information and display the generated order information. Of course, after the order is generated, the method may further include: after detecting the payment of the order, sending the order to the server of the target client, and receiving the order execution status returned by the server. Among them, during the payment process, the voice assistant supports invoking a third-party payment service provider for payment, for example, WeChat payment or Alipay payment, and can also support invoking a payment server configured corresponding to the voice assistant itself for payment.

For example, as a way, if a designated touch operation on the card is detected, detailed information of the target takeaway merchant is displayed, and the detailed information includes the product information of the target takeaway merchant. Optionally, if a sliding operation in a specified direction acting on the card is detected, the detailed information of the takeaway merchant is displayed on the card. For example, as shown in FIG. 9, after the voice assistant detects that there is a sliding operation on the card 92a in the direction indicated by the arrow, it can display the specific product A, product B, and product C shown in the figure on the right. Then in this manner, the step of generating an order based on the selected target merchant information determined from the target takeaway merchant information includes generating an order based on the selected target product information determined from the target merchant's product information.

The present application provides an information recommendation method. After the voice assistant starts to receive voice information, when the voice information is received, the received voice information is recognized, and if the received voice information is recognized When the takeaway related information is included in the voice assistant, obtain the takeaway merchant information that matches the user portrait of the user bound to the voice assistant as the target takeaway merchant information to be recommended, display a card, and display the target takeaway merchant information in the card . Thus, through this method, the user can trigger the display of takeaway related information through voice, and the voice assistant can recommend matching takeaway merchant information to the user according to the user’s portrait, so that the user can quickly obtain the takeaway goods he needs. Furthermore, there is no need to separately start the target client for ordering food, and then through multiple page scrolling to find the food you need, which greatly improves the user experience.

Refer to FIG. 10, an information recommendation method provided by an embodiment of the present application is applied to a language assistant, and the method includes:

Step S210: The voice assistant starts to receive voice information after being started.

Step S220: After receiving the voice information, recognize the received voice information.

Step S230: If it is recognized that the received voice information does not include takeaway related information, the current process is ended.

Step S231: If it is recognized that the received voice information includes takeaway-related information, obtain the stored pre-calculated user portrait parameters, the user portrait parameters representing the category of the user’s interest; based on the user The portrait parameter acquires the corresponding takeaway merchant information as the target takeaway merchant information to be recommended.

It is understandable that in the process of using electronic devices, users may use electronic devices to access the Internet, or use media such as music players, or browse news through news clients, or make online purchases through shopping clients. This operation behavior of the user can reflect some personal preferences of the user. For example, if it is detected that the user often purchases discounted products on the shopping client, then it can be determined that the user is more concerned about the price of the item to a certain extent, then when recommending a takeaway merchant, it is recommended to recommend discounted takeaway products as much as possible, which is beneficial Users increase the conversion rate of recommendations. For another example, if the user often browses articles recommended for some classic food, it can be determined that the user has a higher demand for food, and then some distinctive and high-quality takeaway products can be recommended to the user.

Based on the above situation, as a way, before step S230, it may further include: periodically acquiring the historical operation behavior of the user bound to the voice assistant; based on the historical operation behavior of the user, calculating the interest category matching the user as User portrait parameters.

Specifically, as a method, based on the user's historical operation behavior, the step of calculating the interest category matching the user as the user portrait parameter includes:

Acquire the target behavior dimension corresponding to the user's historical operation among the multiple behavior dimensions.

Optionally, the multiple behavior dimensions include at least two of a media access dimension, a news dimension, a consumption record dimension, and a web page browsing dimension. It is understandable that, in this embodiment, the voice assistant can monitor and recognize each behavior of the user. For example, after detecting that the user purchases a discounted product, the target behavior dimension is determined to be the consumption record dimension. For another example, when it is detected that the user has opened a webpage titled "Classic Food Recommendations", it will be determined that the target behavior dimension is the webpage browsing dimension.

Optionally, multiple interest categories corresponding to each behavior dimension are the same. Specifically, the multiple interest categories corresponding to each behavior dimension include at least two of the price category, the convenience category, and the taste preference category. Then after obtaining the target behavior dimension, the target interest category can be further obtained. The target interest category is an interest category corresponding to the user's historical operation behavior among multiple interest categories corresponding to the target behavior dimension. For example, after detecting the operation behavior of the user purchasing a discounted product, not only the target behavior dimension is determined as the consumption record dimension, but also the target interest category is further determined as the price category. For another example, after detecting that the user has opened a webpage titled "Classic Food Recommendations", not only will the target behavior dimension be determined as the page browsing dimension, but also the target interest category will be further determined as the taste preference category.

Increase the score of the target interest category.

It is understandable that scores can be configured for multiple interest categories in each behavior dimension, where a higher score indicates that the user pays more attention. Then, after determining the target interest category corresponding to the current operation behavior, the score of the target interest category can be increased. For example, you can add 1 point or 2 points each time.

Based on the scores of multiple interest categories corresponding to each behavior dimension, the interest category matching the user is calculated as the user portrait parameter.

It should be noted that the language assistant can start to calculate the interest category matching the user as the user portrait parameter after each increase in the score of a certain interest category in a certain dimension, or it can be periodically calculated as the interest category matching the user As a user portrait parameter.

In the calculation process, as a way, the step of calculating the interest category matching the user as the user portrait parameter based on the scores of the multiple interest categories corresponding to each behavior dimension includes: calculating each of the Multiple intermediate values of interest categories, where the multiple intermediate values of the scores of the same interest category in multiple behavior dimensions are each multiplied by the weight of the respective behavior dimension; the multiple intermediate values of each interest category are summed to obtain each The total score value of each interest category; the interest categories that are ranked by the total score value and satisfy the target condition are used as the interest category matched with the user; and the interest category matched with the user is used as the user portrait parameter.

Here is another example to illustrate the above content.

For example, in a certain calculation process, the behavioral dimensions include web browsing dimensions, news dimensions, and consumption record dimensions. Each behavior dimension corresponds to several interest categories such as price category, convenience category and taste preference category.

Among them, the web browsing dimension has a weight of 0.5, the news dimension has a weight of 0.2, and the consumption record dimension has a weight of 0.3. The scores of interest categories corresponding to each dimension are shown in the following table.

Then you can calculate that the median value of the price category includes 0.5, 0.4, and 1.5, and then the total score of the price category is 2.4. The intermediate value packages 0.5, 0.6, and 0.9 of the convenience class are calculated, and then the total score value of the convenience class is 2.0. The intermediate value packages 0.5, 0.8, and 0.6 of the taste preference category are calculated, and the total score value of the convenience category is 1.9. Then, when the target condition is that the top two interest categories are ranked as the interest categories matching the user, the interest categories matching the user can be calculated to include the price category and the convenience category.

Step S240: Display a card, and display the target takeaway merchant information in the card.

It should be noted that, in some cases, users have certain tendencies in the process of using the voice assistant to order takeaways, and these tendencies will be directly used as recommendations for reference. For example, if it is recognized that the received voice message includes "I want to order a cheap takeaway", then it can be determined that the user tends to order a cheap takeaway at the time, and the voice assistant may not be based on " "Cheap category" is an interest category to calculate the category that matches the user. Then, in this embodiment, as a way, if it is recognized that the takeaway-related information includes a specified interest category, configure the multiple possible categories to exclude the specified interest category; the total score value The step of sorting the interest categories that meet the target condition as the interest categories that match the user includes: sorting the interest categories that meet the target condition by the total score value and the designated interest category as the interest categories that match the user.

In this embodiment, as a way, the method further includes: obtaining a behavior dimension to be processed, where the behavior dimension to be processed is a behavior dimension that has no corresponding historical operation behavior in a plurality of periods; The behavior dimension to be processed is deleted from the multiple behavior dimensions, and the weights of the remaining behavior dimensions in the multiple behavior dimensions are adjusted accordingly, so that the sum of the weights of the remaining behavior dimensions is 1.

In this embodiment, as a way, the method further includes: obtaining a category of interest to be processed, where the category of interest to be processed is that the ranking of the total score value in a plurality of the periods does not satisfy the target Conditional interest category; delete the to-be-processed interest category from the multiple interest categories.

This application provides an information recommendation method, through which the user can trigger the display of takeaway related information through voice, and the voice assistant can recommend matching takeaway merchant information to the user according to the user’s portrait, which can make the user faster Obtain the takeaway products you need, and you don’t need to start the target client for ordering takeaways separately, and then you can find the takeaways you need through multiple page scrolling, which greatly improves the user experience. And in the process of matching the target takeaway merchant information based on the user portrait, the target takeaway merchant information of the matching user will be calculated based on multiple dimensions and multiple interest categories corresponding to each dimension, thereby improving the accuracy and matching of the recommendation , Which greatly improves the user experience.

Refer to FIG. 11, an information recommendation method provided by an embodiment of the present application is applied to a language assistant, and the method includes:

Step S310: The voice assistant starts to receive voice information after being started.

Step S320: After receiving the voice information, recognize the received voice information.

Step S321: If it is recognized that the received voice information does not include takeaway related information, end the current process.

Step S331: If it is recognized that the received voice information includes takeaway-related information, identify whether the takeaway-related information includes mode information about a pre-configured ordering mode of takeaway.

Step S340: If the identification includes pre-configured mode information, obtain product information of the merchant corresponding to the mode information.

As a way, if the mode information is recognized as the favorite mode, obtain the favorite product information in the favorite merchant configured by the user; if the mode information is recognized as the most recent mode, obtain the takeaway that the user recently ordered Merchant and takeaway product information; and if it is recognized that the mode information is the most mode, obtain the takeaway merchant and takeaway product information with the most orders placed by the user.

Step S350: Generate an order based on the commodity information of the merchant corresponding to the mode information.

As a way, the step of generating an order based on the product information of the merchant corresponding to the mode information includes: displaying the product information of the merchant corresponding to the mode information; if the voice information for confirming the order is recognized, based on The commodity information of the merchant corresponding to the mode information generates an order.

In one manner, after acquiring the product information of the merchant corresponding to the mode information, the voice assistant can directly generate an order based on the acquired product information.

As another way, after obtaining the product information of the merchant corresponding to the mode information, the product information of the merchant corresponding to the mode information may be displayed first. If the voice information for confirming the order is recognized, based on the information The mode information corresponds to the merchandise information of the merchant to generate an order. For example, if the voice assistant recognizes that the user says "I want to order my favorite takeaway", the voice assistant may directly obtain pre-configured favorite products to generate an order after recognizing that there is "favorite" mode information. Of course, in another way, after the voice assistant recognizes the "favorite" mode information, it can first display the product corresponding to the "favorite" mode information in the form of the aforementioned card, and then recognize that there is "favorite" mode information. After similar semantics such as "Place an order" or "just this" are confirmed, an order is generated based on the product information of the merchant corresponding to the mode information.

In addition, for example, when the voice assistant recognizes that the user said "the same takeaway as last time", the voice assistant can recognize that the mode information is the most recent, and then it can directly generate an order based on the last order.

Step S360: If it is recognized that the takeaway related information does not include the pre-configured mode information, obtain the target takeaway merchant information to be recommended, where the target takeaway merchant information is the takeaway merchant information matching the user portrait of the user bound to the voice assistant .

Step S370: Display a card, and display the target takeaway merchant information in the card.

This application provides an information recommendation method, through which the user can trigger the display of takeaway related information through voice, and the voice assistant can recommend matching takeaway merchant information to the user according to the user’s portrait, which can make the user faster Obtain the takeaway products you need, and you don’t need to start the target client for ordering takeaways separately, and then you can find the takeaways you need through multiple page scrolling, which greatly improves the user experience. In addition, based on the pre-configured mode information, the product information of the merchant corresponding to the mode information can be obtained as the target takeaway merchant information for recommendation, thereby enhancing the flexibility of recommendation.

Please refer to FIG. 12, an information recommendation apparatus 400 provided by an embodiment of the present application, the apparatus 400 includes:

The voice information receiving unit 410 is configured to receive voice information after the voice information processing device is started.

The voice recognition unit 420 is configured to recognize the received voice information after receiving the voice information.

The takeaway information obtaining unit 430 is configured to obtain information about a target takeaway merchant to be recommended if it is recognized that the received voice information includes takeaway related information, where the target takeaway merchant information is a user bound to the voice assistant The information of the takeaway merchant matched by the user profile.

The information display unit 440 is configured to display a card, and display the target takeaway merchant information in the card.

As a way, the information display unit 440 is specifically configured to: if it is recognized that the user portrait parameter indicates that the user has multiple interest categories; to display multiple cards, each card displays target takeaway merchant information corresponding to one interest category.

Among them, as a way, the takeaway information obtaining unit 430 is specifically configured to obtain stored pre-calculated user portrait parameters, where the user portrait parameters characterize the category of the user’s interest in commodities; and obtain corresponding user portrait parameters based on the user portrait parameters. The takeaway merchant information is used as the target takeaway merchant information to be recommended.

As shown in FIG. 13, the device 400 further includes a user portrait calculation unit 450, configured to periodically obtain the historical operation behavior of the user bound to the voice assistant; based on the historical operation behavior of the user, calculate the interest matching the user The category is used as the user portrait parameter.

The portrait calculation unit 450 is specifically configured to obtain the target behavior dimension corresponding to the user's historical operation among the multiple behavior dimensions; to obtain the target interest category, where the target interest category is the same among the multiple interest categories corresponding to the target behavior dimension. The interest category corresponding to the user's historical operation behavior, where multiple interest categories corresponding to each behavior dimension are the same; increase the score of the target interest category;

The portrait calculation unit 450 is specifically configured to calculate multiple intermediate values for each of the interest categories, where the multiple intermediate values are the values obtained by multiplying the scores of the same interest category in the multiple behavior dimensions by the weight of the corresponding behavior dimension; Sum multiple intermediate values of each interest category to obtain the total score value of each interest category;

The interest categories that are ranked by the total score value and satisfy the target conditions are used as the interest categories matched with the user; the interest categories matched with the user are used as the user portrait parameters.

Wherein, the multiple behavior dimensions include at least two of media access dimensions, news dimensions, consumption record dimensions, and web page browsing dimensions. The multiple interest categories include at least two of price category, convenience category, and taste preference category.

As a way, the portrait calculation unit 450 is specifically configured to configure the plurality of possible categories to exclude the specified interest category if it is recognized that the takeaway-related information includes the specified interest category; the total score is The step of sorting the interest categories satisfying the target condition by value as the interest categories matching the user includes: sorting the interest categories satisfying the target condition by the total score value and the specified interest category as the interest categories matching the user.

As a way, the portrait calculation unit 450 is specifically configured to obtain a behavior dimension to be processed, where the behavior dimension to be processed is a behavior dimension that has no corresponding historical operation behavior in multiple periods; The behavior dimension of is deleted from the multiple behavior dimensions, and the weights of the remaining behavior dimensions in the multiple behavior dimensions are adjusted accordingly, so that the sum of the weights of the remaining behavior dimensions is 1.

As a way, the portrait calculation unit 450 is specifically configured to obtain the interest category to be processed, and the interest category to be processed is the interest category for which the total score value ranking in the plurality of periods does not satisfy the target condition. ; Delete the interest category to be processed from the multiple interest categories.

As shown in FIG. 14, the device 400 further includes an information detection unit 460 and an order generation unit 470. The information detection unit 460 is configured to identify whether the takeaway-related information includes mode information about a pre-configured ordering mode of take-out, and if the recognition includes pre-configured mode information, obtain product information of a merchant corresponding to the mode information. The order generation unit 470 is configured to generate an order based on the product information of the merchant corresponding to the mode information; if it is recognized that the takeaway-related information does not include the pre-configured mode information, execute the acquisition of the target takeaway merchant information to be recommended. Optionally, the information detection unit 460 is specifically configured to obtain the favorite product information in the favorite merchant configured by the user if the mode information is recognized as the favorite mode; if the mode information is recognized as the most recent mode, obtain The takeaway merchant and takeaway product information of the last time the user placed an order; and if the mode information is identified as the most mode, the takeaway merchant and takeaway product information that the user has placed the most orders.

The order generating unit 470 is specifically configured to display product information of the merchant corresponding to the mode information;

If the voice information for confirming the order is recognized, an order is generated based on the product information of the merchant corresponding to the mode information. The order generating unit 470 is further configured to obtain the information of the takeaway merchant to be placed determined from the target takeaway merchant information; and generate an order based on the information of the takeaway merchant to be placed.

In one manner, the takeaway information obtaining unit 430 is specifically configured to send a target takeaway merchant information obtaining request to be recommended to the server of the target client, and receive the target takeaway merchant information to be recommended returned by the server. In this manner, as shown in FIG. 14, the device 400 further includes an order processing unit 480, which is configured to send the order to the server after detecting the payment of the order, and receive the return from the server. Order execution status.

It should be noted that the device embodiment in this application and the foregoing method embodiment correspond to each other, and the specific principles in the device embodiment can be referred to the content in the foregoing method embodiment, which is not repeated here.

An electronic device provided by the present application will be described below in conjunction with FIG. 15.

Referring to FIG. 15, based on the foregoing information recommendation method and device, an embodiment of the present application also provides another electronic device 200 that can execute the foregoing information recommendation method. The electronic device 200 includes one or more (only one is shown in the figure) a processor 102, a memory 104, and a network module 106 coupled to each other. Wherein, the memory 104 stores a program that can execute the content in the foregoing embodiment, and the processor 102 can execute the program stored in the memory 104.

The processor 102 may include one or more processing cores. The processor 102 uses various interfaces and lines to connect various parts of the entire electronic device 200, and executes by running or executing instructions, programs, code sets, or instruction sets stored in the memory 104, and calling data stored in the memory 104. Various functions and processing data of the electronic device 200. Optionally, the processor 102 may use at least one of digital signal processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA). A kind of hardware form to realize. The processor 102 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a modem, and the like. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is used for rendering and drawing of display content; the modem is used for processing wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 102, but may be implemented by a communication chip alone.

The memory 104 may include random access memory (RAM) or read-only memory (Read-Only Memory). The memory 104 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 104 may include a storage program area and a storage data area, where the storage program area may store instructions for implementing the operating system and instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.) , Instructions for implementing the following method embodiments, etc. The data storage area can also store data (such as phone book, audio and video data, chat record data) created by the terminal 100 during use.

The network module 106 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices, such as with audio playback devices. The network module 106 may include various existing circuit elements for performing these functions, for example, an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a subscriber identity module (SIM) card, a memory, etc. . The network module 106 can communicate with various networks such as the Internet, an intranet, and a wireless network, or communicate with other devices through a wireless network. The aforementioned wireless network may include a cellular telephone network, a wireless local area network, or a metropolitan area network. For example, the network module 106 can exchange information with the base station.

Please refer to FIG. 16, which shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application. The computer-readable medium 1100 stores program code, and the program code can be invoked by a processor to execute the method described in the foregoing method embodiment.

The computer-readable storage medium 1100 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 1100 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 1100 has a storage space for executing the program code 810 of any method step in the foregoing method. These program codes can be read out from or written into one or more computer program products. The program code 1110 may be compressed in a suitable form, for example.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the application, not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions recorded in the foregoing embodiments are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not drive the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

An information recommendation method, characterized in that it is applied to a voice assistant, and the method includes:

The voice assistant starts to receive voice information after being started;

After receiving the voice information, recognize the received voice information;

If it is recognized that the received voice information includes takeaway related information, obtain the target takeaway merchant information to be recommended, where the target takeaway merchant information is the takeaway merchant information that matches the user profile of the user bound to the voice assistant ；

A card is displayed, and the target takeaway merchant information is displayed in the card.
The method according to claim 1, wherein the step of obtaining information of the target takeaway merchant to be recommended comprises:

Acquiring stored pre-calculated user portrait parameters, where the user portrait parameters represent the category of the user's interest product;

Obtain corresponding takeaway merchant information based on the user portrait parameter as the target takeaway merchant information to be recommended.
The method according to claim 2, wherein before the step of obtaining the stored pre-calculated user portrait parameters, the method further comprises:

Periodically acquiring the historical operation behavior of the user bound to the voice assistant;

Based on the historical operation behavior of the user, the interest category matching the user is calculated as the user portrait parameter.
The method according to claim 3, wherein the step of calculating, based on the historical operation behavior of the user, an interest category matching the user as a user portrait parameter comprises:

Acquiring a target behavior dimension corresponding to the user's historical operation among multiple behavior dimensions;

Acquiring a target interest category, where the target interest category is an interest category corresponding to the user's historical operation behavior among multiple interest categories corresponding to the target behavior dimension, wherein the multiple interest categories corresponding to each behavior dimension are the same;

Increase the score of the target interest category;

Based on the scores of multiple interest categories corresponding to each behavior dimension, the interest category matching the user is calculated as the user portrait parameter.
The method according to claim 4, wherein the step of calculating the interest category matching the user as the user portrait parameter based on the scores of the multiple interest categories corresponding to each behavior dimension comprises:

Calculating multiple intermediate values of each of the interest categories, where the multiple intermediate values are the values obtained by multiplying the scores of the same interest category in multiple behavior dimensions by the weight of the corresponding behavior dimension;

Sum multiple intermediate values of each interest category to obtain the total score value of each interest category;

Sort the interest categories that meet the target conditions by the total score value as the interest categories that match the user;

The interest category matched with the user is used as the user portrait parameter.
The method according to claim 4 or 5, wherein the multiple behavior dimensions include at least two of a media access dimension, a news dimension, a consumption record dimension, and a web browsing dimension.
The method according to claim 4 or 5, wherein the multiple interest categories include at least two of a price category, a convenience category, and a taste preference category.
The method according to claim 7, wherein the method further comprises:

If it is recognized that the designated interest category is included in the food-related information, configure the plurality of possible categories to exclude the designated interest category;

The step of sorting the interest categories satisfying the target condition by the total score value as the interest categories matching the user includes:

Sort the interest categories that meet the target condition by the total score value and the specified interest categories as the interest categories that match the user.
The method according to claim 4 or 5, wherein the method further comprises:

Acquiring a behavior dimension to be processed, where the behavior dimension to be processed is a behavior dimension that has no corresponding historical operation behavior in multiple periods;

The behavior dimension to be processed is deleted from the multiple behavior dimensions, and the weights of the remaining behavior dimensions in the multiple behavior dimensions are adjusted accordingly, so that the sum of the weights of the remaining behavior dimensions is 1.
The method according to claim 9, wherein the method further comprises:

Acquiring a category of interest to be processed, where the category of interest to be processed is an interest category that does not satisfy the target condition in the order of the total score value in multiple periods;

The to-be-processed interest category is deleted from the multiple interest categories.
The method according to any one of claims 2-10, wherein the step of displaying the card and displaying the target takeaway merchant information in the card comprises:

If it is recognized that the user portrait parameter indicates that the user has multiple interest categories;

Display multiple cards, and each card displays the target takeaway merchant information corresponding to an interest category.
The method according to any one of claims 1-11, wherein before the step of obtaining information of the target takeaway merchant to be recommended, the method further comprises:

Identify whether the takeaway-related information includes mode information about the pre-configured ordering mode for takeaway,

If the identification includes pre-configured mode information, obtain product information of the merchant corresponding to the mode information;

Generating an order based on the commodity information of the merchant corresponding to the mode information;

If it is recognized that the takeaway-related information does not include the pre-configured mode information, the acquisition of the target takeaway merchant information to be recommended is performed.
The method according to claim 12, wherein if the identification includes pre-configured mode information, the step of obtaining product information of a merchant corresponding to the mode information comprises:

If it is recognized that the mode information is the favorite mode, obtain the favorite product information in the favorite merchant configured by the user;

If it is recognized that the mode information is the most recent mode, obtain the takeaway merchant and takeaway product information of the last order placed by the user; and

If it is recognized that the mode information is the most mode, the takeaway merchants with the most orders placed by the user and takeaway product information are obtained.
The method according to claim 12, wherein the step of generating an order based on the commodity information of the merchant corresponding to the mode information comprises:

Display product information of the merchant corresponding to the mode information;

If the voice information for confirming the order is recognized, an order is generated based on the product information of the merchant corresponding to the mode information.
The method according to any one of claims 1-11, wherein after the step of displaying the card and displaying the target takeaway merchant information in the card, the method further comprises:

Acquiring information of the takeaway merchant to be ordered determined from the target takeaway merchant information;

An order is generated based on the information of the takeaway merchant to be placed.
The method according to claim 15, wherein the step of obtaining information of the target takeaway merchant to be recommended comprises:

Sending the target takeaway merchant information acquisition request to be recommended to the server of the target client, and receiving the target takeaway merchant information to be recommended returned by the server;

After the step of generating an order based on the information of the takeaway merchant to be placed, the step further includes:

After detecting the payment of the order, the order is sent to the server, and the order execution status returned by the server is received.
The method according to any one of claims 1-16, wherein the takeaway-related information includes: I want to order takeaway, order takeaway, or takeaway.
An information recommendation device, characterized in that the device includes:

A voice information receiving unit for receiving voice information after the voice information processing device is started;

The voice recognition unit is used to recognize the received voice information after receiving the voice information;

The takeaway information acquisition unit is configured to obtain the target takeaway merchant information to be recommended when it is recognized that the received voice information includes takeaway related information, and the target takeaway merchant information is the information of the user bound to the voice assistant Information of takeaway merchants matching user portraits;

The information display unit is used to display the card, and display the target takeaway merchant information in the card.
An electronic device, characterized in that it includes one or more processors and a memory;

One or more programs are stored in the memory and configured to be executed by the one or more processors to implement the method of any one of claims 1-17.
A computer-readable storage medium, wherein a program code is stored in the computer-readable storage medium, wherein the method according to any one of claims 1-17 is executed when the program code is run by a processor.