CN113330475B

CN113330475B - Information recommendation method, device, electronic equipment and storage medium

Info

Publication number: CN113330475B
Application number: CN201980089699.4A
Authority: CN
Inventors: 郭子亮
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd; Shenzhen Huantai Technology Co Ltd
Priority date: 2019-05-20
Filing date: 2019-05-20
Publication date: 2024-06-04
Anticipated expiration: 2039-05-20
Also published as: WO2020232616A1; CN113330475A

Abstract

The embodiment of the application discloses an information recommendation method, an information recommendation device, electronic equipment and a storage medium. The method comprises the following steps: the voice assistant starts to receive voice information after starting; after receiving the voice information, identifying the received voice information; if the received voice information is identified to comprise takeaway related information, acquiring target takeaway merchant information to be recommended, wherein the target takeaway merchant information is takeaway merchant information matched with the user portrait of the voice assistant binding user; and displaying a card and displaying the target take-away merchant information in the card. The method realizes that the user triggers and displays the takeaway related information through voice, and the voice assistant can recommend the matched takeaway merchant information to the user according to the portrait of the user, so that the user can acquire the takeaway commodity required by the user more quickly, and the user experience is greatly improved.

Description

Information recommendation method, device, electronic equipment and storage medium

Technical Field

The present application relates to the field of internet of things, and in particular, to an information recommendation method, an apparatus, an electronic device, and a storage medium.

Background

With the development of voice recognition technology, more electronic devices are provided with voice assistants to interact with users of the electronic devices, and during the interaction with the voice assistants, the users can complete part of operations through the voice assistants, however, the related voice assistants are not related to the takeaway field yet.

Disclosure of Invention

In view of the above, the present application proposes an information recommendation method, apparatus, electronic device, and storage medium to improve the above-mentioned problems.

In a first aspect, the present application provides an information recommendation method, applied to a voice assistant, the method including: the voice assistant starts to receive voice information after starting; after receiving the voice information, identifying the received voice information; if the received voice information is identified to comprise takeaway related information, acquiring target takeaway merchant information to be recommended, wherein the target takeaway merchant information is takeaway merchant information matched with the user portrait of the voice assistant binding user; and displaying a card and displaying the target take-away merchant information in the card.

In a second aspect, an information recommendation method, the apparatus includes: a voice information receiving unit for receiving voice information after the voice information processing device is started; the voice recognition unit is used for recognizing the received voice information after receiving the voice information; the takeout information acquisition unit is used for acquiring target takeout merchant information to be recommended if the received voice information comprises takeout related information, wherein the target takeout merchant information is takeout merchant information matched with the user portrait of the binding user of the voice assistant; and the information display unit is used for displaying a card and displaying the target take-away merchant information in the card.

In a third aspect, the present application provides an electronic device comprising 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 executed by the one or more processors to perform the methods described above.

In a fourth aspect, the present application provides a computer readable storage medium having program code stored therein, wherein the above method is performed when the program code is run, and wherein control confusion is avoided.

According to the information recommending method, the device, the electronic equipment and the storage medium, after the voice assistant starts to receive voice information after starting, when the voice assistant receives the voice information, the received voice information is identified, if the received voice information is identified to include takeaway related information, takeaway merchant information matched with the user portrait of the user bound by the voice assistant is obtained as target takeaway merchant information to be recommended, a card is displayed, and the target takeaway merchant information is displayed in the card. According to the method, the user can trigger and display the takeaway related information through voice, and the voice assistant can recommend matched takeaway merchant information to the user according to the portrait of the user, so that the user can acquire the takeaway commodity required by the user more quickly, the target client for point takeaway is not required to be independently started, and then the user can search the takeaway required by the user through multiple page sliding, and therefore user experience is greatly improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flowchart of a method for processing voice information according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a voice information collection interface according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a take-away voice setup interface according to an embodiment of the present application;

FIG. 4 is a schematic diagram showing the addition result of a take-away voice setting interface according to an embodiment of the present application;

FIG. 5 is a schematic diagram illustrating communication between a voice assistant and a server of a target take-away client according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a card according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a multi-card display according to an embodiment of the present application;

FIG. 8 is a schematic diagram of card switching according to an embodiment of the present application;

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

FIG. 10 is a flowchart of a method for processing voice information according to another embodiment of the present application;

FIG. 11 is a flowchart of a voice information processing method according to still another embodiment of the present application;

Fig. 12 is a block diagram showing a configuration of a voice information processing apparatus according to an embodiment of the present application;

fig. 13 is a block diagram showing a structure of a voice information processing apparatus according to another embodiment of the present application;

Fig. 14 is a block diagram showing a structure of a voice information processing apparatus according to still another embodiment of the present application;

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

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

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

With the development of speech recognition technology, electronic devices, such as smartphones, tablet computers, and computers, are equipped with intelligent speech assistants. Such as Siri for apples, bixby for samsung, google Assistant, amazon Alex, etc. The voice assistant can be regarded as an intelligent application, and the user can help the user to solve some practical problems or replace the user to operate the electronic device by intelligently interacting with the voice assistant through intelligent dialogue and instant question-answering.

For example, in a related scenario, the voice assistant of the electronic device may recognize that the user intends to use the hundred degree map when detecting that the user input "help me open the hundred degree map", and may start the hundred degree map. In another related scenario, the voice assistant of the electronic device may recognize that the user is desiring to find a parking lot within a certain range when detecting that the user input has "where there is a parking lot nearby", and then the electronic device may perform a search of the parking lot based on the location and display the search result.

However, the inventor finds out in the research of the voice assistant that the related voice assistant cannot well recognize the semantics of the takeaway related information input by the user, or even can respond, the related voice assistant cannot bring better user experience to the user. For example, in one approach, after identifying a user input point take-out or take-out, the associated voice assistant either performs a search for resources in a search engine-like manner using "point take-out" or "take-out" as keywords, and then displays the text material searched for, or perhaps directly searches for nearby restaurants for presentation. However, the inventor finds that the response of the relevant voice assistant to the takeaway relevant information is not the real intention of the user, and thus the experience of the user cannot be improved and the actual requirement of the user cannot be met. Furthermore, the inventor also finds that in the process of directly adopting the related takeaway software to take a takeaway order, the user needs to repeatedly slide the page for many times to find the required commodity, and further the user experience is poor.

Accordingly, the inventors have proposed a voice information processing method, apparatus, electronic device, and storage medium in the present application that can improve the above-described problems. The method provided by the embodiment of the application can realize that the user can trigger and display the related information of the takeout through voice, and can directly complete the operation of ordering in a voice assistant, so that a target client for taking out is not required to be independently started, and then the user can search the takeout required by the user through multiple page sliding, thereby greatly improving the user experience. Moreover, the method realizes that the user triggers and displays the takeaway related information through voice, and the voice assistant can recommend the matched takeaway merchant information to the user according to the portrait of the user, so that the user can acquire the takeaway commodity required by the user more quickly.

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

Referring 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 begins receiving voice information after startup.

Wherein it will be appreciated that the voice assistant may be an application running independently in the electronic device. Or may be a component configured in a certain application. In the use process of the user, the user can trigger the voice assistant to start by touching a physical key of the electronic equipment, and can also trigger the voice assistant to start by touching a virtual key displayed by the electronic equipment.

For example, as one way, where the electronic device is provided with a HOME key, the electronic device may configure the associated target application or a component of the target application as a voice assistant where a long press or double press of the HOME key is preconfigured to trigger the associated target application to launch, or where a long press or double press of the HOME key is triggered to launch a component of the associated target application, thereby enabling a long press or double press of the HOME key to trigger the voice assistant to launch.

Alternatively, the electronic device may be configured with a touch-sensitive display screen, and the electronic device may be configured with a portal in the desktop of the system or in some application that triggers the voice assistant to start. In this case the desktop configures a voice assistant portal, the portal may be a desktop application icon named voice assistant, while in this case a portal is configured in a certain application that triggers the voice assistant to launch, the portal is a control, such as a text control or a button control, that may be named voice assistant.

When the voice assistant is started, the electronic device may display an interface as shown in fig. 2, after which the electronic device triggers the configured microphone or other physical voice capturing element to start capturing voice, so that the started voice assistant may acquire the captured voice information.

Step S120: and after receiving the voice information, identifying the received voice information.

It will be appreciated that for the voice information received by the voice assistant to be a voice signal, the voice assistant also needs to convert the voice information in the form of the voice signal into the voice information in the form of text, and this conversion process is a process of recognizing the received voice information.

In the embodiment of the application, the voice assistant can realize the recognition of the received voice information in various modes.

As a way, the API (Application Programming Interface ) of the third party speech recognition system may be preconfigured, in which way the speech assistant may transmit the sound signal to be recognized to the third party for recognition based on the preconfigured API of the third party speech recognition system, and then receive the speech information in text form returned by the third party. For example, the API of a third party speech recognition system provided by Microsoft or Google may be employed.

Alternatively, the neural network model may be trained in advance to obtain a model having speech information in the form of a sound signal converted into speech information in the form of text. And then the trained model is deployed in a designated server or service cluster, so that the voice assistant can transmit the voice information in the form of the received voice signal to the server or service cluster for recognition in the process of needing to recognize the received voice information, and then the voice information in the form of the recognized text returned by the server or service cluster is received.

In yet another approach, the voice assistant may perform recognition at the API calling the third party voice recognition system and transmit to a designated server or service cluster for real-time selection of the recognition to enhance the flexibility of the recognition.

In this manner, the voice assistant may optionally determine which form of recognition to perform based on the current network state. It can be understood that the communication process is more stable when the network is accessed directly through the WIFI hotspot than when the network is accessed through the mobile communication base station, so that the voice assistant can call the API of the third party voice recognition system to recognize when the network is accessed through the WIFI mode currently, and transmit the identification to the designated server or service cluster to recognize when the network is accessed through the mobile communication base station currently.

Furthermore, the voice assistant can also switch the recognition modes through the recognition success rate. It will be appreciated that different users will have different pronunciation habits or speaking patterns, and even for the same recognition pattern, different recognition results will occur due to the user's own pronunciation habits or speaking patterns. In this case, the voice assistant can switch the recognition modes according to the habit of the user and the success rate of the combined recognition. The voice assistant can judge that the recognition fails under the condition that the user repeatedly recognizes similar voice signals. The voice assistant may switch to another recognition mode after recognizing that the specified number of failures have occurred in one recognition mode. For example, if the voice assistant starts to use the API that calls the third party voice recognition system to perform recognition, and detects that three similar voice signals are continuously recognized (the designated number of times is 3), then it is determined to switch to transmitting to the server or the service cluster for recognition. It should be noted that, the similar sound signals may be determined by determining the error energy of the two sound signals.

Step S130: and if the received voice information is identified to not include takeaway related information, ending the current flow.

Step S131: and if the received voice information is identified to comprise takeaway related information, acquiring target takeaway merchant information to be recommended, wherein the target takeaway merchant information is takeaway merchant information matched with the user portrait of the voice assistant binding user.

Wherein, take-away related information includes: i am the point take-away, point take-away or take-away.

It will be appreciated that the voice assistant may trigger the takeaway merchant information to be obtained after identifying some specific information, such as target takeaway merchant information to be recommended. And the specific information therein includes takeaway related information, which may include "i am key point takeaway", "point takeaway", or "takeaway", etc. In this way, when the voice assistant recognizes that the received voice information includes takeaway related information, it is determined that the user wishes to take away, and then target takeaway merchant information to be recommended is obtained.

There are various configurations of takeaway related information.

As a way, several pieces of statistically derived common take-away related information may be configured by default at the time of voice assistant installation. For example, "i am gist take-away", "point take-away", or "take-away" as described above, and the like.

Furthermore, as another way, the configuration can be performed by the user according to the own needs. As user demands change, more users desire more personalized ways to control electronic devices. For example, some users like to say "i am to eat" or like to say "i am hungry", etc., and then in order to allow the voice assistant to adapt to users with different language expression habits, the configuration of take-away related information by the user may be configured.

For example, as shown in FIG. 3, a take-away related information addition control 97 and a presentation control 96 to which take-away related information has been added are included in the take-away language settings interface 98 shown in FIG. 3. And further new takeaway related information may be added after the user clicks the takeaway related information adding control 97. And in addition to being added in text form, the sound signal can be added at the same time. For example, when the user clicks the take-out related information adding control 97 to trigger the user to enter the take-out related information in the form of sound, for example, after the user inputs "i want to eat", the corresponding sound signal of "i want to eat" is stored at the same time, except that the display control 96 of the take-out related information displays the text form of "i want to eat". In this way, after receiving the voice information, the language assistant can directly compare the received voice signal with the pre-stored voice signal to improve the final feedback effect, and it can be understood that the comparison signal can be used to determine whether the received voice signal and the pre-stored voice signal are similar in the process of comparing the voice signals, if so, the takeaway merchant information can be directly obtained without performing subsequent language-to-text conversion recognition.

In the embodiment of the application, the language assistant can acquire the information of the target takeout merchant to be recommended in a plurality of modes.

As one approach, the language assistant may obtain target take-away merchant information to be recommended based on a data interface with the target take-away client. In this way, the language assistant sends an information acquisition request to the target takeout client, wherein the information acquisition request is used for triggering the target takeout client to acquire target takeout merchant information to be recommended according to a specified rule; and receiving target take-out merchant information returned by the target client to be recommended. In this manner, as shown in fig. 5, the voice assistant sends the information acquisition request to the target takeaway client through the communication channel 95, the target takeaway client may first query whether there is takeaway merchant information cached locally, if so, directly return to the voice assistant, and if it detects that there is no takeaway merchant information cached, send the request for takeaway merchant information to the server through the communication channel 94, and then return to the voice assistant sequentially through the communication channel 94 and the communication channel 95. It will be appreciated that the target take-away client herein is a client that may be used to independently complete take-away order generation and placement. Similar to the beauty take out client or starving the client.

In another way, an information acquisition request is sent to a server corresponding to a target takeout client, wherein the information acquisition request is used for triggering the server to acquire takeout merchant information according to a specified rule;

and receiving target takeout merchant information to be recommended returned by the server. For example, referring to fig. 5 again, in this manner, the voice assistant directly sends the information obtaining request to the server through the communication channel 93, and still returns the information of the target takeout merchant to be recommended to the voice assistant through the communication channel 93.

In yet another manner, the language assistant may forward the information acquisition request to the server through the target takeout client, and the server directly returns the information of the target takeout merchant to be recommended to the voice assistant without converting through the target takeout client, thereby improving the information transmission rate. It will be appreciated that for devices other than the electronic device in which the voice assistant is located, the applications are distinguished by the port number they occupy. For example, the browser client occupies 80 ports and the voice assistant occupies 8080 ports, then if the returned information is directed to 8080 ports, 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 in generating the information acquisition request, and when the server generates the returned information, the port number of the voice assistant is added in the returned information, so that the information can be directly sent to the voice assistant.

It should be noted that, the target takeout merchant information to be recommended in this embodiment may include takeout merchant information of takeout merchants closest to the current location of the user based on multiple dimensions, or takeout merchant information of several takeout merchants with matching distribution ranges with the user and higher evaluation, or takeout merchant information of takeout merchants directly adapting to the user history of the commodity, or, of course, takeout merchant information mixed by the above rules. In the present embodiment, the specific rule is not particularly limited, and one or more of the above-described various rules may be mixed and adopted. The specified rule used may be replaced periodically.

Step S140: and displaying a card and displaying the target take-away merchant information in the card.

After the target take-away merchant information to be recommended is acquired, the target take-away merchant information may be displayed in a card 92 as shown in fig. 6. The target takeout merchant information may include a merchant name, score information, sales volume delivery price, commodity type, and the like of the takeout merchant. In addition, the information of the takeaway merchant can also directly comprise some commodities with higher sales volume or special commodities.

Of course, as a way, the voice assistant may detect the amount of the target take-away merchant information; and if the number of the target takeout merchant information is detected to be a plurality of, displaying a plurality of cards, wherein each card correspondingly displays one target takeout merchant information. For example, as shown in fig. 7, in case that 3 take-out merchant information is recognized, 3 cards 92a, 92b and 92c may be displayed to display the 3 target take-out merchant information, respectively. In addition, if the number of the target take-out merchant information is identified to be unable to be directly displayed in the same interface, only part of the target take-out merchant information can be displayed first, further after the user is detected to slide towards the upper side of the screen, more merchant information is loaded for displaying, and meanwhile part of the target take-out merchant information which is displayed before is hidden. For example, in the interface shown in fig. 8, when the user detects that the user slides the screen in the direction indicated by the arrow, the card 92a that is ranked closest to the direction indicated by the arrow is hidden, and a new card 92e is loaded for display.

It will be appreciated that the step of displaying the card and displaying the target take-away merchant information in the card further comprises: acquiring takeout merchant information to be ordered, which is determined from the target takeout merchant information; and generating an order based on the takeout merchant information to be ordered.

After the target takeout merchant information is displayed, the user can further control, so that the voice assistant displays more information, and the user can select the required commodity to be ordered.

The voice assistant can send the selected target merchant information to the target client after acquiring the target merchant information selected by the user, wherein the selected target merchant information is used for triggering the target client to generate order information and displaying the generated order information. It will be appreciated that in this manner, the voice assistant will trigger the target client to switch to the foreground display, which in turn will 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 order payment, sending the order to a server side of a target client side, and receiving order execution conditions returned by the server side. In the payment process, the voice assistant supports to call a third party payment service provider to make payment, for example, weChat payment or Payment device payment, and also can support to call a payment server configured corresponding to the voice assistant to make payment.

For example, as one mode, if a specific touch operation acting on the card is detected, detailed information of the target takeout merchant is displayed, where the detailed information includes commodity information of the target takeout merchant. Optionally, if a sliding operation acting on the card along the designated direction is detected, detailed information of the takeout merchant is displayed in the card. For example, as shown in fig. 9, when the voice assistant detects a sliding operation in the direction indicated by the arrow on the card 92a, the voice assistant can display information about the specific products a, B, C, etc. shown in the right-hand diagram. In this manner, then, the step of generating an order based on the target merchant information determined to be selected from the target take-away merchant information includes: an order is generated based on selected target merchandise information determined from the merchandise information of the target merchant.

According to the information recommendation method provided by the application, after the voice assistant starts to receive voice information after starting, when the voice information is received, the received voice information is identified, if the received voice information is identified to include takeaway related information, takeaway merchant information matched with the user portrait of the user bound by the voice assistant is obtained as target takeaway merchant information to be recommended, a card is displayed, and the target takeaway merchant information is displayed in the card. According to the method, the user can trigger and display the takeaway related information through voice, and the voice assistant can recommend matched takeaway merchant information to the user according to the portrait of the user, so that the user can acquire the takeaway commodity required by the user more quickly, the target client for point takeaway is not required to be independently started, and then the user can search the takeaway required by the user through multiple page sliding, and therefore user experience is greatly improved.

Referring 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 begins receiving voice information after startup.

Step S220: and after receiving the voice information, identifying the received voice information.

Step S230: and if the received voice information is identified to not include takeaway related information, ending the current flow.

Step S231: if the received voice information is identified to comprise takeaway related information, acquiring stored pre-calculated user portrait parameters, wherein the user portrait parameters represent the types of interesting commodities of the user; and acquiring corresponding takeaway merchant information based on the user portrait parameters as target takeaway merchant information to be recommended.

It will be appreciated that in the process of using the electronic device, the user may access the internet using the electronic device, or use media such as a music player, or browse news through a news client, and then make online purchases through a shopping client, etc. And this operational behavior for the user may reflect some personal preferences of the user. For example, if it is detected that the user frequently purchases the discount commodity at the shopping client, it can be determined that the user compares the price of the favorite commodity to a certain extent, and when recommending the takeaway merchant, the discount takeaway commodity is recommended as much as possible, which is beneficial to improving the recommendation conversion rate for the user. For another example, if the user frequently browses recommended articles for some classical food, it may be determined that the user has a higher best for the diet, and then some featured and higher quality take-away merchandise may be recommended to the user.

Then, based on the above, as a way, before step S230, it may further include: periodically acquiring the historical operation behaviors of the binding user of the voice assistant; and calculating interest categories matched with the user based on the historical operation behaviors of the user to serve as user portrait parameters.

Specifically, as a way, the step of calculating the interest category matched with the user as the user portrait parameter based on the historical operation behavior of the user includes:

and acquiring a target behavior dimension corresponding to the user history operation in a plurality of behavior dimensions.

Optionally, the plurality of behavior dimensions includes at least two of a media access dimension, a news dimension, a consumption record dimension, and a web browsing dimension. It will be appreciated that in this embodiment, the voice assistant may monitor and identify each of the user's actions. For example, upon detecting that a user purchased a piece of discounted merchandise, the target behavior dimension is determined to be the consumption record dimension. For another example, when it is detected that the user opens a web page titled "classical food recommendation", the target behavior dimension is determined to be the web page browsing dimension.

Optionally, the plurality of interest categories corresponding to each behavior dimension are the same. Specifically, the plurality of interest categories corresponding to each behavior dimension include at least two of a price category, a convenience category, and a taste preference category. Then after the target behavior dimension is obtained, the target interest category may be further obtained. The target interest category is an interest category corresponding to the historical operation behavior of the user in a plurality of interest categories corresponding to the target behavior dimension. For example, after detecting that the user has purchased a piece of discounted merchandise, 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 opens a webpage titled "classical food recommendation", not only the target behavior dimension is determined as the webpage browsing dimension, but also the target interest category is further determined as the taste preference category.

And increasing the score of the target interest category.

It will be appreciated that multiple interest categories for each behavior dimension may be correspondingly configured with scores, wherein a higher score characterizes a user's increased interest. Then the score for the target interest category may be increased after the target interest category corresponding to the current operational activity is determined. For example, 1 minute or 2 minutes may be added each time.

And calculating the interest category matched with the user based on the scores of the interest categories corresponding to each behavior dimension, and taking the interest category as a user portrait parameter.

It should be noted that, after each score of a certain interest category in a certain dimension is added, the language assistant may start to calculate the interest category matched with the user as the user portrait parameter, or may periodically calculate the interest category matched with the user as the user portrait parameter.

In the calculating process, as a way, the step of calculating the interest category matched with the user as the user portrait parameter based on the scores of the interest categories corresponding to each behavior dimension includes: calculating a plurality of intermediate values of each interest category, wherein the plurality of intermediate values are values obtained by multiplying scores of the same interest category in a plurality of behavior dimensions by weights of the behavior dimensions; summing the plurality of intermediate values of each interest category to obtain a total scoring value of each interest category; ordering the total score values into interest categories meeting the target conditions as interest categories matched with the user; and taking the interest category matched with the user as a user portrait parameter.

The above will be described by way of an example.

For example, in some computing process, the behavior dimension includes a web browsing dimension, a news dimension, and a consumption record dimension. Each behavior dimension corresponds to a price class, a convenience class, and a taste preference class for several interest categories.

The weight of the web page browsing dimension is 0.5, the weight of the news dimension is 0.2, and the weight of the consumption record dimension is 0.3. And the scores for interest categories corresponding to each dimension are shown in the table below.

Then the intermediate values of the price class can be calculated to include 0.5, 0.4 and 1.5, resulting in a total score value of 2.4 for the price class. And calculating to obtain intermediate value packages 0.5, 0.6 and 0.9 of the convenience class, and further obtaining the total grading value of the convenience class as 2.0. And calculating to obtain intermediate value packages 0.5, 0.8 and 0.6 of the taste preference class, and further obtaining the total grading value of the convenience class as 1.9. Then, in the case that the target condition is that the interest category ranked 2 earlier is the interest category matched with the user, the interest category matched with the user can be calculated to include a price category and a convenience category.

Step S240: and displaying a card and displaying the target take-away merchant information in the card.

It should be noted that, in some cases, the user may have a certain tendency during the process of taking out the voice assistant, and these tendencies will be directly referred to as recommendations. For example, if it is recognized that "i want to take an inexpensive take-away" is included in the received voice information, then it may be determined that the current user is inclined to take an inexpensive take-away, and the voice assistant may not be used to calculate a category matching the user based on the interest category "inexpensive category". In this embodiment, if the takeaway related information includes a specified interest category, the multiple interest categories are configured to exclude the specified interest category; the step of sorting the total score values into interest categories satisfying the target condition as interest categories matching the user includes: and ordering the total score value into interest categories meeting the target condition, and taking the appointed interest categories as interest categories matched with the user.

In this embodiment, as one manner, the method further includes: acquiring a behavior dimension to be processed, wherein the behavior dimension to be processed is a behavior dimension without corresponding historical operation behaviors in a plurality of periods; deleting the behavior dimension to be processed from the plurality of behavior dimensions, and correspondingly adjusting the weights of the remaining behavior dimensions in the plurality of behavior dimensions so that the sum of the weights of the remaining behavior dimensions is 1.

In this embodiment, as one manner, the method further includes: obtaining an interest category to be processed, wherein the interest category to be processed is an interest category of which the total grading value ranking in a plurality of periods does not meet the target condition; and deleting the interest category to be processed from the interest categories.

According to the information recommendation method provided by the application, the user can trigger and display the related information of the take-out through voice, and the voice assistant can recommend the matched take-out merchant information to the user according to the portrait of the user, so that the user can acquire the required take-out commodity faster, the target client for taking out is not required to be independently started, and then the required take-out is searched through multiple page sliding, thereby greatly improving the user experience. In the process of matching the target take-away merchant information based on the user portrait, the target take-away merchant information matched with the user is calculated based on a plurality of dimensions and a plurality of interest categories corresponding to each dimension, so that the accuracy and the matching degree of recommendation are improved, and the user experience is greatly improved.

Referring 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 begins receiving voice information after startup.

Step S320: and after receiving the voice information, identifying the received voice information.

Step S321: and if the received voice information is identified to not include takeaway related information, ending the current flow.

Step S331: and if the received voice information is identified to include takeaway related information, identifying whether the takeaway related information includes mode information about a preconfigured takeaway mode.

Step S340: and if the identification comprises the pre-configured mode information, acquiring commodity information of the merchant corresponding to the mode information.

As a way, if the mode information is identified as the favorite mode, obtaining favorite commodity information in favorite merchants configured by the user; if the mode information is identified as the latest mode, acquiring takeaway merchants and takeaway commodity information of the latest order of the user; and if the mode information is identified as the most mode, acquiring takeaway merchants with the most user orders and takeaway commodity information.

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

In one mode, the step of generating the order based on the commodity information of the merchant corresponding to the pattern information includes: displaying commodity information of merchants corresponding to the mode information; and generating an order based on the commodity information of the merchant corresponding to the mode information after identifying the voice information confirming the order.

In one mode, after the voice assistant obtains the commodity information of the merchant corresponding to the mode information, the voice assistant may directly generate the order based on the obtained commodity information.

Alternatively, after acquiring the commodity information of the merchant corresponding to the mode information, the commodity information of the merchant corresponding to the mode information may be displayed first, and if the voice information confirming the order is recognized, an order is generated based on the commodity information of the merchant corresponding to the mode information. For example, if the voice assistant recognizes that the user says "i am the favorite take away," the voice assistant recognizes that the user has the "favorite" mode information, or directly obtains the preconfigured favorite commodity generation order. Of course, in another mode, after recognizing that the mode information of "favorite" exists, the voice assistant may display the commodity corresponding to the mode information of "favorite" in the form of the card, and then recognize that the semantics of "order bar" or "about this" and the like are confirmed, and then generate an order based on the commodity information of the merchant corresponding to the mode information.

In addition, for example, when the voice assistant recognizes that the user speaks "take-out as last," the voice assistant can recognize that the mode information is the last time, and then the voice assistant can directly generate an order according to the commodity ordered last time.

Step S360: and if the takeout related information is identified not to comprise the pre-configured mode information, acquiring target takeout merchant information to be recommended, wherein the target takeout merchant information is takeout merchant information matched with the user portrait of the voice assistant binding user.

Step S370: and displaying a card and displaying the target take-away merchant information in the card.

According to the information recommendation method provided by the application, the user can trigger and display the related information of the take-out through voice, and the voice assistant can recommend the matched take-out merchant information to the user according to the portrait of the user, so that the user can acquire the required take-out commodity faster, the target client for taking out is not required to be independently started, and then the required take-out is searched through multiple page sliding, thereby greatly improving the user experience. And commodity information of merchants corresponding to the mode information can be obtained as target takeout merchant information for recommendation based on the pre-configured mode information at the same time, so that the flexibility of recommendation can be enhanced.

Referring to fig. 12, an information recommendation apparatus 400 provided in an embodiment of the present application, the apparatus 400 includes:

A voice information receiving unit 410 for receiving voice information after the voice information processing apparatus is started.

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

And the take-out information obtaining unit 430 is configured to obtain target take-out merchant information to be recommended if it is identified that the received voice information includes take-out related information, where the target take-out merchant information is take-out merchant information matched with the user portrait of the voice assistant binding user.

And an information display unit 440 for displaying a card and displaying the target take-away merchant information in the card.

As one way, the information display unit 440 is specifically configured to characterize the user as having a plurality of interest categories if the user profile parameter is identified; and displaying a plurality of cards, wherein each card displays target takeout merchant information corresponding to one interest category.

Wherein, as a way, the take-out information obtaining unit 430 is specifically configured to obtain a stored pre-calculated user portrait parameter, where the user portrait parameter characterizes a category of a commodity of interest of the user; and acquiring corresponding takeaway merchant information based on the user portrait parameters as target takeaway merchant information to be recommended.

As shown in FIG. 13, the apparatus 400 further includes a user profile calculation unit 450 for periodically obtaining the voice assistant binding user historical operation behavior; and calculating interest categories matched with the user based on the historical operation behaviors of the user to serve as user portrait parameters.

The portrait computing unit 450 is specifically configured to obtain a target behavior dimension corresponding to the user history operation from multiple behavior dimensions; acquiring a target interest category, wherein the target interest category is an interest category corresponding to the historical operation behavior of the user in a plurality of interest categories corresponding to the target behavior dimension, and the plurality of interest categories corresponding to each behavior dimension are the same; increasing the score of the target interest category;

The portrait calculating unit 450 is specifically configured to calculate a plurality of intermediate values of each of the interest categories, where the plurality of intermediate values are values obtained by multiplying scores of the same interest category in a plurality of behavior dimensions by weights of the behavior dimensions; summing the plurality of intermediate values of each interest category to obtain a total scoring value of each interest category;

ordering the total score values into interest categories meeting the target conditions as interest categories matched with the user; and taking the interest category matched with the user as a user portrait parameter.

Wherein the plurality of behavior dimensions includes at least two of a media access dimension, a news dimension, a consumption record dimension, and a web browsing dimension. The plurality of interest categories includes at least two of a price category, a convenience category, and a taste preference category.

As one way, the portrait computing unit 450 is specifically configured to configure the plurality of permission categories to exclude the specified interest category if it is identified that the takeaway related information includes the specified interest category; the step of sorting the total score values into interest categories satisfying the target condition as interest categories matching the user includes: and ordering the total score value into interest categories meeting the target condition, and taking the appointed interest categories as interest categories matched with the user.

As a way, the portrait computing unit 450 is specifically configured to obtain a behavior dimension to be processed, where the behavior dimension to be processed is a behavior dimension in which no corresponding historical operation behaviors exist in a plurality of periods; deleting the behavior dimension to be processed from the plurality of behavior dimensions, and correspondingly adjusting the weights of the remaining behavior dimensions in the plurality of behavior dimensions so that the sum of the weights of the remaining behavior dimensions is 1.

As one way, the portrait computing unit 450 is specifically configured to obtain an interest category to be processed, where the interest category to be processed is an interest category in which the total score ranks in a plurality of periods do not satisfy the target condition; and deleting the interest category to be processed from the interest categories.

As shown in fig. 14, the apparatus 400 further includes an information detection unit 460 and an order generation unit 470. The information detecting unit 460 is configured to identify whether the takeout related information includes mode information about a preconfigured takeout mode, and if the identification includes the preconfigured mode information, acquire commodity information of a merchant corresponding to the mode information. The order generation unit 470 is configured to generate an order based on the commodity information of the merchant corresponding to the pattern information; and if the takeout related information is identified not to include the pre-configured mode information, executing the acquisition of the target takeout merchant information to be recommended. Optionally, the information detection unit 460 is specifically configured to obtain favorite merchandise information in a favorite merchant configured by a user if the mode information is identified as a favorite mode; if the mode information is identified as the latest mode, acquiring takeaway merchants and takeaway commodity information of the latest order of the user; and if the mode information is identified as the most mode, acquiring takeaway merchants with the most user orders and takeaway commodity information.

An order generation unit 470, specifically configured to display commodity information of a merchant corresponding to the pattern information;

And generating an order based on the commodity information of the merchant corresponding to the mode information after identifying the voice information confirming the order. The order generation unit 470 is further configured to obtain takeout merchant information to be placed in an order determined from the target takeout merchant information; and generating an order based on the takeout merchant information to be ordered.

In one manner, the takeout information obtaining unit 430 is specifically configured to send a target takeout merchant information obtaining request to be recommended to a server side of a target client side, and receive target takeout merchant information to be recommended returned by the server side. In this manner, as shown in fig. 14, the apparatus 400 further includes an order processing unit 480, configured to send the order to the server after detecting the payment of the order, and receive the order execution condition returned by the server.

It should be noted that, in the present application, the device embodiment and the foregoing method embodiment correspond to each other, and specific principles in the device embodiment may refer to the content in the foregoing method embodiment, which is not described herein again.

An electronic device according to the present application will be described with reference to fig. 15.

Referring to fig. 15, based on the above information recommendation method and apparatus, another electronic device 200 capable of executing the above information recommendation method is provided in the embodiment of the present application. The electronic device 200 includes one or more (only one shown) processors 102, memory 104, and network modules 106 coupled to one another. The memory 104 stores therein a program capable of executing the contents of the foregoing embodiments, and the processor 102 can execute the program stored in the memory 104.

Wherein the processor 102 may include one or more processing cores. The processor 102 utilizes various interfaces and lines to connect various portions of the overall electronic device 200, perform various functions of the electronic device 200, and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 104, and invoking data stored in the memory 104. Alternatively, the processor 102 may be implemented in hardware in at least one of digital signal Processing (DIGITAL SIGNAL Processing, DSP), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 102 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for being responsible for rendering and drawing of display content; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 102 and may be implemented solely by a single communication chip.

The Memory 104 may include random access Memory (Random Access Memory, RAM) or Read-Only Memory (ROM). Memory 104 may be used to store instructions, programs, code sets, or instruction sets. The memory 104 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (e.g., a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described below, etc. The storage data area may also store data created by the terminal 100 in use (such as phonebook, audio-video data, chat-record data), etc.

The network module 106 is configured to receive and transmit electromagnetic waves, and to implement mutual conversion between the electromagnetic waves and the electrical signals, so as to communicate with a communication network or other devices, such as an audio playing device. The network module 106 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and the like. The network module 106 may communicate with various networks such as the Internet, intranets, wireless networks, or other devices via wireless networks. The wireless network may include a cellular telephone network, a wireless local area network, or a metropolitan area network. For example, the network module 106 may interact with base stations.

Referring to fig. 16, a block diagram of a computer readable storage medium according to an embodiment of the present application is shown. The computer readable medium 1100 has stored therein program code that can be invoked by a processor to perform the methods described in the method embodiments above.

The computer readable storage medium 1100 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, computer readable storage medium 1100 includes non-volatile computer readable media (non-transitory computer-readable storage medium). The computer readable storage medium 1100 has storage space for program code 810 that performs any of the method steps described above. The program code can be read from or written to one or more computer program products. Program code 1110 may be compressed, for example, in a suitable form.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be appreciated by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An information recommendation method, applied to a voice assistant, comprising:

the voice assistant starts to receive voice information after starting;

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

if the received voice information is identified to comprise takeaway related information, acquiring target takeaway merchant information to be recommended, wherein the target takeaway merchant information is takeaway merchant information matched with the user portrait of the voice assistant binding user;

the step of obtaining information of the target takeout merchant to be recommended comprises the following steps:

Periodically acquiring the historical operation behaviors of the binding user of the voice assistant;

acquiring a target behavior dimension corresponding to the historical operation behavior of the user from a plurality of behavior dimensions;

acquiring a target interest category, wherein the target interest category is an interest category corresponding to the historical operation behavior of the user in a plurality of interest categories corresponding to the target behavior dimension, and the plurality of interest categories corresponding to each behavior dimension are the same;

Increasing the score of the target interest category;

calculating a plurality of intermediate values of each interest category, wherein the plurality of intermediate values are values obtained by multiplying scores of the same interest category in a plurality of behavior dimensions by weights of the behavior dimensions;

Summing the plurality of intermediate values of each interest category to obtain a total scoring value of each interest category;

ordering the total score values into interest categories meeting target conditions as interest categories matched with the user;

The interest category matched with the user is used as a user portrait parameter;

acquiring stored pre-calculated user portrait parameters, wherein the user portrait parameters represent the types of interesting commodities of a user;

acquiring corresponding takeaway merchant information based on the user portrait parameters as target takeaway merchant information to be recommended;

displaying a card and displaying the target take-away merchant information in the card;

acquiring takeout merchant information to be ordered, which is determined from the target takeout merchant information;

And generating an order based on the takeout merchant information to be ordered.

2. The method of claim 1, wherein the plurality of behavior dimensions includes at least two of a media access dimension, a news dimension, a consumption record dimension, and a web browsing dimension.

3. The method of claim 1, wherein the plurality of interest categories includes at least two of a price category, a convenience category, and a taste preference category.

4. A method according to claim 3, characterized in that the method further comprises:

If the takeaway related information is identified to comprise the appointed interest category, configuring the plurality of interest categories to exclude the appointed interest category;

The step of sorting the total score values into interest categories satisfying the target condition as interest categories matching with the user includes:

And ordering the total score value into interest categories meeting the target condition, and taking the appointed interest categories as interest categories matched with the user.

5. The method according to claim 1, wherein the method further comprises:

Acquiring a behavior dimension to be processed, wherein the behavior dimension to be processed is a behavior dimension without corresponding historical operation behaviors in a plurality of periods;

deleting the behavior dimension to be processed from the plurality of behavior dimensions, and correspondingly adjusting the weights of the remaining behavior dimensions in the plurality of behavior dimensions so that the sum of the weights of the remaining behavior dimensions is 1.

6. The method of claim 5, wherein the method further comprises:

Obtaining an interest category to be processed, wherein the interest category to be processed is an interest category of which the total grading value ranking in a plurality of periods does not meet the target condition;

and deleting the interest category to be processed from the interest categories.

7. The method of any one of claims 1-6, wherein the step of displaying a card and displaying the targeted take-away merchant information in the card comprises:

if the user portrait parameters are identified to represent a plurality of interest categories of the user;

And displaying a plurality of cards, wherein each card displays target takeout merchant information corresponding to one interest category.

8. A method according to any one of claims 1-6, wherein the step of obtaining target take-away merchant information to be recommended further comprises, prior to:

identifying whether the take-away related information includes mode information regarding a preconfigured order take-away mode,

If the identification comprises the pre-configured mode information, acquiring commodity information of a merchant corresponding to the mode information;

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

and if the takeout related information is identified not to include the pre-configured mode information, executing the acquisition of the target takeout merchant information to be recommended.

9. The method of claim 8, wherein if the identification includes pre-configured pattern information, the step of acquiring merchandise information of the merchant corresponding to the pattern information includes:

If the mode information is identified as the favorite mode, obtaining favorite commodity information in favorite merchants configured by the user;

If the mode information is identified as the latest mode, acquiring takeaway merchants and takeaway commodity information of the latest order of the user; and

And if the mode information is identified as the most mode, acquiring the takeaway merchant with the most user orders and takeaway commodity information.

10. The method of claim 9, wherein the generating an order based on the commodity information of the merchant corresponding to the pattern information comprises:

displaying commodity information of merchants corresponding to the mode information;

And generating an order based on the commodity information of the merchant corresponding to the mode information after identifying the voice information confirming the order.

11. The method of claim 1, wherein the step of obtaining target take-away merchant information to be recommended comprises:

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

The step of generating the order based on the takeout merchant information to be placed further comprises the following steps:

after detecting the order payment, sending the order to the server, and receiving order execution conditions returned by the server.

12. A method according to any one of claims 1-6, wherein the take-away related information comprises: i am the point take-away, point take-away or take-away.

13. An information recommendation device, characterized in that the device comprises:

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

The voice recognition unit is used for recognizing the received voice information after receiving the voice information;

The takeaway information acquisition unit is used for acquiring target takeaway merchant information to be recommended if the received voice information comprises takeaway related information, wherein the target takeaway merchant information is takeaway merchant information matched with the user portrait of the binding user of the voice information receiving unit; the step of obtaining information of the target takeout merchant to be recommended comprises the following steps: periodically acquiring the historical operation behaviors of the binding user of the voice information receiving unit; acquiring a target behavior dimension corresponding to the historical operation behavior of the user from a plurality of behavior dimensions; acquiring a target interest category, wherein the target interest category is an interest category corresponding to the historical operation behavior of the user in a plurality of interest categories corresponding to the target behavior dimension, and the plurality of interest categories corresponding to each behavior dimension are the same; increasing the score of the target interest category; calculating a plurality of intermediate values of each interest category, wherein the plurality of intermediate values are values obtained by multiplying scores of the same interest category in a plurality of behavior dimensions by weights of the behavior dimensions; summing the plurality of intermediate values of each interest category to obtain a total scoring value of each interest category; ordering the total score values into interest categories meeting target conditions as interest categories matched with the user; the interest category matched with the user is used as a user portrait parameter; acquiring stored pre-calculated user portrait parameters, wherein the user portrait parameters represent the types of interesting commodities of a user; acquiring corresponding takeaway merchant information based on the user portrait parameters as target takeaway merchant information to be recommended;

the information display unit is used for displaying a card and displaying the target take-away merchant information in the card;

The information acquisition unit of the business to be ordered is used for acquiring information of the business to be ordered, which is determined from the information of the target business to be ordered;

and the order placing unit is used for generating an order based on the takeout merchant information to be placed.

14. An electronic device comprising one or more processors and memory;

one or more programs are stored in the memory and configured to be executed by the one or more processors to implement the methods of any of claims 1-12.

15. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program code, wherein the program code, when being executed by a processor, performs the method of any of claims 1-12.