WO2020232615A1 - 信息推荐方法、装置、电子设备以及存储介质 - Google Patents

信息推荐方法、装置、电子设备以及存储介质 Download PDF

Info

Publication number
WO2020232615A1
WO2020232615A1 PCT/CN2019/087665 CN2019087665W WO2020232615A1 WO 2020232615 A1 WO2020232615 A1 WO 2020232615A1 CN 2019087665 W CN2019087665 W CN 2019087665W WO 2020232615 A1 WO2020232615 A1 WO 2020232615A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
product information
user
behavior
target
Prior art date
Application number
PCT/CN2019/087665
Other languages
English (en)
French (fr)
Inventor
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 (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to PCT/CN2019/087665 priority Critical patent/WO2020232615A1/zh
Priority to CN201980090665.7A priority patent/CN113366524B/zh
Publication of WO2020232615A1 publication Critical patent/WO2020232615A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions

Definitions

  • This application relates to the field of Internet of Things, and more specifically, to an information recommendation method, device, electronic equipment, and storage medium.
  • voice assistants to interact with users of electronic devices.
  • users can use voice assistants to complete some operations.
  • voice assistants has not yet been involved in the shopping field.
  • this application proposes an information recommendation method, device, electronic equipment, and storage medium to improve the above problems.
  • 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; when the voice information is received, the received voice Information; if it is recognized that the received voice information includes shopping-related information, obtain the target product information to be recommended associated with the shopping-related information from the target product information providing platform, and the target product information is The voice assistant binds the product information matching the user portrait of the user; a card is displayed, and the target product information is displayed in the card.
  • the present application provides an information recommendation device, the device includes: a voice information receiving unit, configured to start receiving voice information after the information recommendation device is started; a voice recognition unit, configured to receive voice information After that, the received voice information is recognized; the product information acquisition unit is configured to, if it is recognized that the received voice information includes shopping-related information, obtain information related to the shopping from the target product information providing platform Information-related target product information to be recommended, where the target product information is product information matching the user portrait of the user bound to the voice assistant; an information display unit for displaying a card, and displaying the Target product information.
  • 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.
  • 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.
  • the voice assistant starts to receive voice information
  • the voice information is received
  • the received voice information is recognized.
  • the received voice information includes shopping-related information
  • Determine the product information that matches the user portrait of the user then display a card, and display the target product information in the card.
  • the user can trigger the display of shopping-related information through voice, and the voice assistant can recommend matching target product information to the user according to the user's portrait, so that the user can obtain the product he needs faster, and then There is no need to start the target client for shopping separately, and then find the goods you need through multiple page scrolling, which greatly improves the user experience.
  • Fig. 1 shows a flowchart of an information recommendation method proposed by 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 shopping voice setting interface proposed by an embodiment of the present application
  • FIG. 4 shows a schematic diagram of a result of adding a shopping 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 for providing commodity information 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 product information according to an embodiment of the present application.
  • FIG. 10 shows a flowchart of an information recommendation method proposed by another embodiment of the present application.
  • FIG. 11 shows a flowchart of an information recommendation method proposed by still another embodiment of the present application.
  • FIG. 12 shows a flowchart of an information recommendation method proposed by another embodiment of the present application.
  • FIG. 13 shows a structural block diagram of a voice information processing device proposed by an embodiment of the present application.
  • FIG. 14 shows a structural block diagram of a voice information processing device proposed by another embodiment of the present application.
  • FIG. 15 shows a structural block diagram of a voice information processing device proposed by another embodiment of the present application.
  • FIG. 16 shows a structural block diagram of an electronic device of the present application for executing the information recommendation method according to an embodiment of the present application
  • Fig. 17 is a storage unit for storing or carrying program code for implementing the information recommendation method according to the embodiment of the present application.
  • 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.
  • 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.
  • 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.
  • the inventor found in the research on voice assistants that the related voice assistants still cannot well recognize the semantics of shopping-related information entered by users, or even if they can respond, they cannot bring users a better user experience. .
  • the relevant voice assistant After the relevant voice assistant recognizes the user’s input that I want to buy something, it either uses "buy something" or "something" as a keyword to perform a resource search similar to a search engine, and then displays the searched Text information, or it may be directly searched for nearby shopping malls for display.
  • the response of the related voice assistant to the shopping-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.
  • the inventor also found that in the process of placing an order directly using related shopping software, the user needs to repeatedly slide the page to find the product he needs, which will also cause a poor user experience.
  • the inventor proposes an information recommendation method, device, electronic device, and storage medium that can improve the above problems in this application.
  • the user can trigger the display of shopping related information through voice, and the voice assistant can follow the user's portrait Recommend matching target product information to users, so that users can get the products they need faster, and there is no need to start the target client for shopping separately, and then find their own products through multiple page slides.
  • Required commodities which greatly improves the user experience.
  • an information recommendation method provided by an embodiment of the present application is applied to a voice assistant, and the method includes:
  • Step S110 The voice assistant starts to receive voice information after being started.
  • 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.
  • the electronic device when the electronic device is set 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.
  • the electronic device 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.
  • 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.
  • Voice Assistant for example, a text control or a button control.
  • 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.
  • the voice assistant has multiple ways to realize the recognition of the received voice information.
  • the API Application Programming Interface
  • 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.
  • the API of a third-party speech recognition system provided by Microsoft or Google can be used.
  • 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.
  • the voice assistant can call the API of a third-party voice recognition system for recognition, and transmit it to a designated server or service cluster for recognition for real-time selection, so as to enhance the flexibility of recognition.
  • 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.
  • the voice assistant can switch the recognition mode according to the user's own habits and combined with the recognition success rate.
  • the voice assistant can determine that the recognition fails when it detects that the user has repeatedly recognized similar sound signals.
  • 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 shopping-related information, the current process is ended.
  • Step S131 If it is recognized that the received voice information includes shopping-related information, obtain the target product information to be recommended associated with the shopping-related information from the target product information providing platform, and the target product information is The voice assistant binds the product information matching the user portrait of the user.
  • shopping-related information includes: I want to buy things, I want to shop, I want to shop on Pinduoduo, etc. It is understandable that the voice assistant will only trigger to obtain the target product providing platform and product information after it recognizes some specific information. For example, target product information to be recommended.
  • the specific information includes shopping-related information, and the shopping-related information may include "I want to buy something", "buy something” or "shopping". In this way, when the voice assistant recognizes that the received voice information includes shopping-related information, it determines that the user wants to shop, and then obtains the target product information to be recommended.
  • the shopping language setting interface 98 shown in FIG. 3 includes a shopping-related information addition control 97 and a display control 96 to which shopping-related information has been added. Furthermore, after the user clicks the shopping-related information adding control 97, new shopping-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.
  • the voice assistant receives the voice information, in order to improve the final feedback effect, it can directly compare the received voice signal with the pre-stored voice signal. It is understandable that the voice In the signal process, the aforementioned method of comparing the signal similarity can be used to determine whether the received sound signal is similar to the pre-stored sound signal. If so, the target product information can be directly obtained without further follow-up Language to text conversion recognition, thereby improving the efficiency of information feedback.
  • the voice assistant has multiple ways to obtain the target product information to be recommended.
  • the target commodity information providing platform is the client for providing commodity information.
  • the voice assistant can obtain the target to be recommended based on the data interface with the client for providing commodity information. Commodity information.
  • the voice assistant will send an information acquisition request to the client for providing product information, and the information acquisition request is used to trigger the client for providing product information to obtain the product to be recommended according to specified rules.
  • Target product information; receiving the client for providing product information returns the target product information to be recommended.
  • the voice assistant will first use the communication channel 95 to send the information acquisition request to the client for providing product information.
  • the client for providing product information can first query whether there is a local cache. If there is any target product information, it will be directly returned to the voice assistant. If it detects that there is no cached target product information, it will send a request for obtaining target product information to the server based on the communication channel 94, and then pass through the communication channel 94 and the communication channel in turn 95 returns to the voice assistant.
  • the client used to provide product information is a client that can be used to independently complete shopping order generation and order placement, similar to the Pinduoduo client or Taobao client.
  • an information acquisition request is sent to a server corresponding to a client for providing product information, and the information acquisition request is used to trigger the server to acquire target product information according to a specified rule; receiving the server Returned target product information.
  • the voice assistant directly sends an information acquisition request to the server through the communication channel 93, and then returns the target product information to be recommended to the voice assistant through the communication channel 93.
  • the voice assistant can forward the information acquisition request to the server through the client for providing product information, and the server directly returns the target product information to be recommended to the voice assistant without passing through The client used to provide product information performs conversion, thereby increasing the information transmission rate.
  • the application program is distinguished by the port number occupied by the application program.
  • 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.
  • the target product information to be recommended in this embodiment may include obtaining product information of the merchants closest to the user’s current location based on multiple dimensions, or it may be that the delivery range matches the user and has a relatively high degree of praise.
  • the product information of the high several merchants can also be the product information of the merchants that directly adapt to the product ordered by the user in the history, of course, it can also be the product information after the above several rules are mixed.
  • the specific specified rule is not specifically limited, and one or more of the foregoing multiple rules may be used in combination.
  • the specified rules used can also be changed periodically.
  • Step S140 Display a card, and display the target product information in the card.
  • the target product information can be displayed in the card 92 as shown in FIG. 6.
  • the target product information may include the name of the merchant, rating information, sales volume, and product type.
  • the voice assistant can detect the quantity of the target commodity information; if it detects that the quantity of the target commodity information is more than one, multiple cards are displayed, and each card corresponds to a target commodity. information. For example, as shown in FIG. 7, when three pieces of target product information are identified, three cards 92a, 92b, and 92c can be displayed respectively to display the three pieces of target product information.
  • the method further includes: obtaining the product information to be ordered determined from the target product information; Single item information generates an order.
  • the user can further manipulate, so that the voice assistant can display more information so that the user can select the desired product to place an order.
  • 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.
  • the method may further include: after detecting the payment of the order, sending the order to the server for the client for providing product information, and receiving the order execution status returned by the server .
  • 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.
  • a third-party payment service provider for payment for example, WeChat payment or Alipay payment
  • a payment server configured corresponding to the voice assistant itself for payment.
  • the voice assistant if a designated touch operation on the card is detected, detailed information of the target product information is displayed, and the detailed information includes a pair of specifications corresponding to the target product information.
  • the detailed information of the target product information is displayed on the card.
  • 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 specifications A, B, and C shown in the figure on the right.
  • the method further includes: acquiring the product information to be ordered determined from the target product information; The product information placed on the order generates an order.
  • the step further includes: after detecting the payment of the order, sending the order to the server, and receiving the order execution status returned by the server.
  • the voice assistant can trigger the activation of the electronic device and the target product information providing platform
  • the corresponding client is started, and the detailed information of the product information touched by the user is loaded in the started client.
  • the client corresponding to the target commodity information providing platform Before triggering the client corresponding to the target commodity information providing platform, it can first detect whether the client is installed in the electronic device where the voice assistant is located. If it is detected that the client is not installed, the The application in the device downloads the interface between the clients to obtain the download page of the client corresponding to the target product information providing platform, and display a new card in the voice assistant, and load the target product information to the new card
  • the download page of the client corresponding to the platform so that even when the electronic device does not install the client corresponding to the target commodity information providing platform, the user does not need to operate the electronic device to switch pages or switch applications directly in the voice assistant Download the required client in the middle, and then improve the user experience.
  • the voice assistant and the application download client can realize data interaction through inter-process communication.
  • the page display mode of the application download client itself is different, and the download page data transmitted to the voice assistant will be correspondingly different.
  • the interface in the application download client is pre-configured in the electronic device, and it just requests data from the corresponding server during the running process. It can be displayed in the interface, that is, in this case, the interface includes the local interface data and the dynamic data requested from the server.
  • the voice assistant cannot directly display the client interface data stored locally, so adaptively, the voice assistant can directly generate a customer bound to the target product information provider platform in the aforementioned new card.
  • the control of the ID of the client, and the ID is obtained by requesting from the application downloading client.
  • the voice assistant will transmit the identification of the client to be downloaded to the application downloading client to trigger the application Download the client to perform the download and installation of the client.
  • the application download client is based on the BS architecture, the interface displayed in the application download client is obtained directly from the server, then the page data requested from the server It is also html-based data, so it can be directly transmitted to the voice assistant for rendering and display.
  • the voice assistant recognizes that the application download client is based on the BS architecture, it can directly request the download page of the client corresponding to the target product information provider platform from the application download client, and place it in a new card Render the download page.
  • the voice assistant will directly request the client data from the server to complete the download and installation, instead of downloading the client through the application.
  • the voice assistant can flexibly and diversely select the generation method of the download interface, which improves the adaptability and success rate of the download, thereby also improving the user experience.
  • 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 shopping-related information is included, obtain the target product information to be recommended associated with the shopping-related information from the target product information providing platform, where the target product information is the product that matches the user portrait of the user bound to the voice assistant Information, and then display a card, and display the target product information in the card.
  • the user can trigger the display of shopping-related information through voice, and the voice assistant can recommend matching target product information to the user according to the user's portrait, so that the user can obtain the product he needs faster, and then There is no need to start the target client for shopping separately, and then find the goods you need through multiple page scrolling, which greatly improves the user experience.
  • an information recommendation method provided by an embodiment of the present application is applied to a voice 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 shopping-related information, the current process is ended.
  • Step S231 If it is recognized that the received voice information includes shopping-related information, obtain the historical operation behavior of the commodity information providing platform used by the voice assistant bound to the user.
  • Step S240 Determine the target commodity information providing platform from the commodity information providing platforms used by the user based on the historical operation behavior.
  • the historical operation behavior includes a plurality of behavior parameters
  • the step of determining a target product information providing platform from the product information providing platform used by the user based on the historical operation behavior includes: based on the used product information Provide multiple behavioral parameters corresponding to each platform, calculate the score of each used product information providing platform; use the used product information providing platform whose score meets the specified conditions as the target product information providing platform.
  • multiple behavioral parameters may include duration of use and number of clicks.
  • the voice assistant can score the product information providing platform based on the respective use time and the number of clicks of each product information providing platform.
  • each behavior parameter corresponds to a score.
  • the score of the behavior parameter corresponding to the triggered behavior can be updated accordingly.
  • the voice assistant can obtain the client terminal currently running on the electronic device in real time, and then can count the running time of the client terminal of a certain commodity information providing platform after running, and use the running time as the usage duration, and then update the corresponding usage duration. Points.
  • the voice assistant detects that the application currently running in the foreground is a client of a product information providing platform, it can count the number of clicks on the current screen in real time as the number of clicks of the client of the product information providing platform running in the foreground.
  • the voice assistant can calculate the use time of the commodity information providing platform A as a parameter, and the number of clicks is b. Then the voice assistant can calculate the commodity information to provide The score of platform A is a+b.
  • each of the behavior parameters corresponds to its own weight, and based on the multiple behavior parameters corresponding to each of the used commodity information providing platforms, the score of each used commodity information providing platform is calculated.
  • the steps include: multiplying the score corresponding to each behavior parameter by the respective weight to obtain multiple parameter scores corresponding to each used product information providing platform; scoring multiple parameters corresponding to each used product information providing platform Add up to get the score corresponding to each used commodity information providing platform.
  • the voice assistant will not directly add the scores corresponding to each behavior parameter to get the score of a certain product information providing platform, but will multiply the score corresponding to each behavior parameter by the weight.
  • the scores are added together to get the score of a certain product information providing platform.
  • the voice assistant statistics obtained the value of the parameter of the use time of commodity information providing platform A as a, and the number of clicks as a parameter of b, and the weight of the use time is 0.6, the number of clicks The weight of is 0.4, then the final score is 0.6*a+0.4*b.
  • the scoring algorithm is relatively simple, and the score of the commodity information providing platform can be obtained more quickly.
  • the importance of a certain behavior parameter will be affected due to the change of the weight, which is conducive to flexibly adjusting the importance of each behavior parameter, so that the final score can be more Good flexibility and real-time.
  • the usage time is reflected by the running time of the client, which characterizes the user's usage habits.
  • the commodity information providing platform For the commodity information providing platform with a longer running time, it is the commodity information providing platform that users are more accustomed to using, and the number of clicks It is the frequency of the user's operation during use, and it characterizes the richness of the product information that the product information providing platform can provide. The more clicks, the richer the information that can be provided. Then if the voice assistant recognizes that the current commodity information providing platform is more suitable for the user's usage habits, the weight corresponding to the duration of use can be increased, and if the voice assistant recognizes that it is more suitable for the platform that can provide more commodity information In the case of, you can increase the weight corresponding to the number of clicks.
  • the voice assistant can obtain the type of each product through the product information interface provided by the product information providing platform, and regard the more types (more than the specified threshold) as common products, and the less number of types ( Less than the specified threshold) as uncommon commodities.
  • Step S250 Obtain the target product information to be recommended associated with the shopping-related information from the target product information providing platform.
  • Step S260 Display a card, and display the target product information in the card.
  • the method further includes: recognizing whether the voice information also includes an identifier of the commodity information providing platform, if not Execute the historical operation behavior of acquiring the commodity information providing platform used by the user bound to the voice assistant, and if so, using the commodity information providing platform also included in the voice information as the target commodity information providing platform.
  • users sometimes have their own clear shopping platform goals, so when users trigger the voice assistant to search for goods, they will send out the information of the shopping platform they expect. For example, if the voice message sent by the user is "I want to buy food on Pinduoduo", the "Pinduoduo" can be recognized as the information of the desired shopping platform.
  • the included product information provides the identity of the platform.
  • This application provides an information recommendation method, through which the user can trigger the display of shopping-related information through voice, and the voice assistant can recommend matching target product information to the user according to the user’s portrait, which can make the user faster Obtain the goods you need, and you do not need to start the target client for shopping separately, and then find the goods you need through multiple page scrolling, which greatly improves the user experience.
  • the user’s historical operation behavior can be used to determine the most matching product information providing platform as the target product information providing platform, so that the user experience can be improved, thereby enabling More quickly and accurately display the product information that matches the user's needs in the shopping platform that users are accustomed to.
  • an information recommendation method provided by an embodiment of the present application is applied to a voice 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 S320 If it is recognized that the received voice information includes shopping-related information, the current process is ended. .
  • Step S331 If it is recognized that the received voice information includes shopping-related information, obtain the target product information to be recommended associated with the shopping-related information from the target product information providing platform, and the target product information is The voice assistant binds the product information matching the user portrait of the user.
  • Step S340 Display a card, and display the target product information in the card.
  • Step S350 When the instruction to replace the commodity information is detected, a commodity information providing platform is determined from the used commodity information providing platforms to obtain target commodity information, and the commodity information providing platform determined is different each time.
  • the voice assistant determines the target product information providing platform and obtains the target product information from the target product information providing platform for display, it is possible that the displayed product information is not what the user needs for the current use, but different products
  • the products that information providing platforms can provide will be different, so even if the search content is the same, the product information provided by different product information providing platforms will be different.
  • the voice assistant counts that there are multiple commodity information providing platforms used by the user, the user can then trigger a replacement platform to search for commodity information.
  • Step S360 Display the target commodity information obtained from the determined commodity information providing platform in the card.
  • Step S370 if it is detected that an order is generated, it is detected whether the ordered commodity belongs to the target commodity corresponding to the target commodity information providing platform.
  • the voice assistant After the voice assistant obtains the target product information returned by the product information providing platform, it will store the target product information and the product information providing platform in the local area, so as to identify the providing platform to which each product information belongs. It is convenient for the voice assistant to recognize the provision platform described in the currently displayed product information.
  • Step S380 If not, obtain a behavior parameter to be processed, where the behavior parameter to be processed is a behavior parameter with the largest weight corresponding to the plurality of behavior parameters. It is understandable that the behavior parameter with the largest corresponding weight value tends to have a greater impact on the final score. However, in the case that the product finally ordered by the user does not belong to the product provided by the original target product information providing platform, the voice assistant can determine that the target product platform fails to provide the product that the user actually expects, so that the impact can be reduced. Determine the weight of the largest behavior parameter of the target product information providing platform, that is, the largest behavior parameter that affects the determination of the target product information providing platform this time as the behavior parameter to be processed.
  • Step S390 Decrease the weight corresponding to the to-be-processed parameter, and increase the weight of behavior parameters other than the to-be-processed behavior parameter among the plurality of behavior parameters.
  • the reduction in the weight of the parameter to be processed in step S390 and the increase in the weight of the behavior parameter other than the behavior parameter to be processed among the plurality of behavior parameters may be general or targeted. Sexual.
  • the voice assistant detects that the current shopping related information is the same as the last time the user finally ordered a product that does not belong to the product provided by the target product information providing platform.
  • the updated weights of multiple behavior parameters are calculated to obtain the current target product information providing platform.
  • the updated weights of multiple behavior parameters are the last time that the voice assistant detected that the user finally ordered a product that does not belong to the target product information providing platform.
  • the weight of multiple behavior parameters updated in the case of the provided goods.
  • the step of reducing the weight corresponding to the parameter to be processed and increasing the weight of the behavior parameter of the plurality of behavior parameters other than the behavior parameter to be processed includes before:
  • the weight of the behavior parameter in the parameters other than the behavior parameter to be processed can be reduced according to the proportion corresponding to the similarity degree. The higher the degree of similarity, the lower the value to be reduced for the weight of the behavior parameter other than the behavior parameter to be processed.
  • the maximum weight reduction is lower than that of the target product information acquired on the target product information providing platform The maximum weight reduction in the case that there is no product that is the same as the product ordered by the user.
  • the target product information provided by the original target product information providing platform includes product A, product B, product C, and product D, and the user ultimately purchases product Z in other product information providing platforms, and the product Z is similar to product B, and among the multiple behavioral parameters corresponding to the current target product information providing platform, the weight of use time is 0.6, and the weight of clicks is 0.4.
  • the similarity of products can be compared through multiple attributes of the products, the more the same attributes, the higher the score.
  • the multiple attributes include product name, product specifications, product price, and estimated delivery time.
  • the voice assistant can correct the accuracy of the platform that ultimately provides the target product information recommended by the user based on real-time data.
  • This application provides an information recommendation method, through which the user can trigger the display of shopping-related information through voice, and the voice assistant can recommend matching target product information to the user according to the user’s portrait, which can make the user faster Obtain the goods you need, and you do not need to start the target client for shopping separately, and then find the goods you need through multiple page scrolling, which greatly improves the user experience.
  • the user after displaying the target product information provided by the target product platform, the user can continue to choose to display the target product information provided by other product providing platforms, thereby achieving convenient access to multiple product providing platforms.
  • an information recommendation method provided by an embodiment of the present application is applied to a voice assistant, and the method includes:
  • Step S410 The voice assistant starts to receive voice information after being started.
  • Step S420 After receiving the voice information, recognize the received voice information.
  • Step S421 If it is recognized that the received voice information does not include shopping-related information, the current process is ended.
  • Step S430 If it is recognized that the received voice information includes shopping-related information, obtain the stored pre-calculated user portrait parameters, the user portrait parameters representing the category of the user's interest product.
  • Step S431 Obtain target product information to be recommended associated with the shopping-related information from the target product information providing platform based on the user portrait parameter, where the target product information matches the user portrait of the user bound to the voice assistant Commodity information.
  • 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, it can be determined that the user is more concerned about the price of the item to a certain extent, and then when recommending product information, recommend the discounted product as much as possible, which is beneficial to the user Improve recommended conversion rate. For another example, if the user often browses articles recommended for some luxury products, it can be determined that the user has a higher demand for the quality of the product, and then some distinctive and high-quality products can be recommended to the user.
  • Step S440 Display a card, and display the target product information in the card.
  • the step further includes: periodically obtaining the historical operation behavior of the voice assistant bound user accessing network resources; based on the user accessing the network The historical operation behavior of the resource, and the interest category matching the user is calculated as the user portrait parameter.
  • the step of calculating an interest category matching the user as a user portrait parameter based on the historical operation behavior of the user accessing network resources includes:
  • 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.
  • 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.
  • target interest category is an interest category corresponding to the historical operation behavior of the user accessing the network resource among the multiple interest categories corresponding to the target behavior dimension, wherein each behavior dimension corresponds to multiple The interest categories are the same.
  • multiple interest categories corresponding to each behavior dimension are the same.
  • 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.
  • 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 "Recommended Classic Nearby Food", 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 convenience category.
  • the score of the target interest category can be increased. For example, you can add 1 point or 2 points each time.
  • the voice 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.
  • 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.
  • the interest category matched with the user is used as the user portrait parameter.
  • 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.
  • the web browsing dimension has a weight of 0.5
  • the news dimension has a weight of 0.2
  • 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.
  • 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.
  • 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.
  • This application provides an information recommendation method, through which the user can trigger the display of shopping-related information through voice, and the voice assistant can recommend matching target product information to the user according to the user’s portrait, which can make the user faster Obtain the goods you need, and you do not need to start the target client for shopping separately, and then find the goods you need through multiple page scrolling, which greatly improves the user experience.
  • the target product information can be determined for the user based on the user's portrait, thereby improving the accuracy and adaptability of product recommendation.
  • an information recommendation device 500 provided by an embodiment of the present application includes: a voice information receiving unit 510, configured to start receiving voice information after the information recommendation device is activated.
  • the voice recognition unit 520 is configured to recognize the received voice information after receiving the voice information.
  • the product information acquisition unit 530 is configured to, if it is recognized that the received voice information includes shopping-related information, obtain the target product information to be recommended associated with the shopping-related information from the target product information providing platform, the The target product information is product information that matches the user portrait of the user bound to the voice assistant.
  • the commodity information obtaining unit 530 is specifically configured to obtain the historical operation behavior of the commodity information providing platform used by the user that is bound to the voice assistant; based on the historical operation behavior from the commodity information providing platform used by the user Determine the target product information providing platform; obtain the target product information to be recommended associated with the shopping-related information from the target product information providing platform.
  • the historical operation behavior includes multiple behavior parameters.
  • the product information obtaining unit 530 is specifically configured to calculate the score of each used product information providing platform based on multiple behavior parameters corresponding to each used product information providing platform; and the score meets the specified conditions Used commodity information providing platform as the target commodity information providing platform.
  • each of the behavior parameters has its own weight.
  • the product information obtaining unit 530 is specifically configured to multiply the score corresponding to each behavior parameter by its respective weight to obtain multiple parameter scores corresponding to each used product information providing platform; The multiple parameter scores corresponding to the used product information providing platform are added to obtain the score corresponding to each used product information providing platform.
  • the product information acquisition unit 530 is configured to provide the product information also included in the voice information when the voice recognition unit 520 recognizes that the voice information also includes the identifier of the product information providing platform
  • the platform serves as a platform for providing target commodity information.
  • the information display unit 540 is configured to display a card and display the target product information in the card. As a way, as shown in FIG.
  • the device further includes: a platform switching unit 550, configured to detect that the user triggers an instruction to switch the commodity information providing platform.
  • the commodity information acquiring unit 530 is specifically configured to determine a commodity information providing platform from the used commodity information providing platforms to obtain target commodity information after detecting an instruction to replace commodity information, and The determined commodity information providing platform is different.
  • the information display unit 540 is specifically configured to display the target product information obtained from the determined product information providing platform in the card.
  • a weight adjustment unit 560 is further included for detecting whether the ordered product belongs to the target product corresponding to the target product information providing platform if it is detected that an order is generated; if not; Belonging to, obtain the behavior parameter to be processed, where the behavior parameter to be processed is the behavior parameter with the largest weight corresponding to the plurality of behavior parameters; reduce the weight corresponding to the parameter to be processed, and increase the number of behavior parameters except for The weight of behavior parameters other than the behavior parameters to be processed.
  • the product information acquiring unit 530 is specifically configured to acquire stored pre-calculated user portrait parameters, where the user portrait parameters represent the category of the user’s interest in the product; based on the user portrait parameters, the target product information A platform is provided to obtain the target product information to be recommended associated with the shopping-related information.
  • the device 500 further includes a portrait parameter calculation unit 570, configured to periodically obtain the historical operation behavior of the voice assistant bound user accessing network resources; based on the user accessing network resources The historical operation behavior of the user is calculated, and the interest category matching the user is calculated as the user portrait parameter.
  • a portrait parameter calculation unit 570 configured to periodically obtain the historical operation behavior of the voice assistant bound user accessing network resources; based on the user accessing network resources The historical operation behavior of the user is calculated, and the interest category matching the user is calculated as the user portrait parameter.
  • the portrait parameter calculation unit 570 is specifically configured to obtain a target behavior dimension corresponding to the historical operation of the user accessing network resources among multiple behavior dimensions; to obtain a target interest category, the target interest category corresponding to the target behavior dimension Among the multiple interest categories in, the interest category corresponding to the historical operation behavior of the user accessing network resources, wherein the multiple interest categories corresponding to each behavior dimension are the same; the score of the target interest category is increased; based on each behavior The scores of multiple interest categories corresponding to the dimensions are calculated, and the interest categories matching the user are calculated as user portrait parameters.
  • the portrait parameter calculation unit 570 is specifically configured to calculate multiple intermediate values of each of the interest categories, and the multiple intermediate values are values of the same interest category in multiple behavior dimensions.
  • the device 500 further includes an order processing unit 580, configured to send a request for obtaining target product information to be recommended to the server of the target client, and to receive the target product information to be recommended returned by the server.
  • 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.
  • 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.
  • 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).
  • DSP Digital Signal Processing
  • FPGA Field-Programmable Gate Array
  • PLA Programmable Logic Array
  • 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.
  • 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.
  • 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. .
  • SIM subscriber identity module
  • 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.
  • the network module 106 can exchange information with the base station.
  • FIG. 18, 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.
  • 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.
  • the present application provides an information recommendation method, device, electronic equipment, and storage medium.
  • the user can trigger the display of shopping-related information through voice, and the voice assistant can recommend matching target product information to the user according to the user's portrait, so that the user can obtain the product he needs faster, and then There is no need to start the target client for shopping separately, and then find the goods you need through multiple page scrolling, which greatly improves the user experience.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请实施例公开了一种信息推荐方法、装置、电子设备以及存储介质。所述方法包括：所述语音助手在启动后开始接收语音信息；当接收到语音信息后，对所述接收到的语音信息进行识别；若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息；显示卡片，并在所述卡片中显示所述目标商品信息。通过本方法实现使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的商品，从而极大的提升了用户体验。

Description

信息推荐方法、装置、电子设备以及存储介质 技术领域
本申请涉及物联网领域，更具体地，涉及一种信息推荐方法、装置、电子设备以及存储介质。
背景技术
随着语音识别技术的发展，更多的电子设备上安装有语音助手来与电子设备的用户进行交互，而用户在与语音助手的交互过程中，可以通过语音助手来完成部分操作，然而相关的语音助手还未涉及到购物领域。
发明内容
鉴于上述问题，本申请提出了一种信息推荐方法、装置、电子设备以及存储介质，以改善上述问题。
第一方面，本申请提供了一种信息推荐方法，应用于语音助手，所述方法包括：所述语音助手在启动后开始接收语音信息；当接收到语音信息后，对所述接收到的语音信息进行识别；若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息；显示卡片，并在所述卡片中显示所述目标商品信息。
第二方面，本申请提供了一种信息推荐装置，所述装置包括：语音信息接收单元，用于在所述信息推荐装置启动后开始接收语音信息；语音识别单元，用于当接收到语音信息后，对所述接收到的语音信息进行识别；商品信息获取单元，用于若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息；信息显示单元，用于显示卡片，并在所述卡片中显示所述目标商品信息。
第三方面，本申请提供了一种电子设备，包括一个或多个处理器以及存储器；一个或多个程序，其中所述一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行上述的方法。
第四方面，本申请提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有程序代码，其中，在所述程序代码运行时执行上述的方法，并且也可以避免控制混乱。
本申请提供的一种信息推荐方法、装置、电子设备以及存储介质，在语音助手在启动后开始接收语音信息后，当接收到语音信息时，对所述接收到的语音信息进行识别，若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息，然后显示卡片，并在所述卡片中显示所述目标商品信息。从而通过本方法实现了用户通过语音来触发显示购物的相关信息，并且语音助手可以根据用户的画像给用户推荐匹配的目标商品信息，进而可以使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的商品，从而极大的提升了用户体验。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1示出了本申请实施例提出的一种信息推荐方法的流程图；
图2示出了本申请实施例提出的一种语音信息采集界面的示意图；
图3示出了本申请实施例提出的一种购物语音设置界面的示意图；
图4示出了本申请实施例提出的一种购物语音设置界面添加结果的示意图；
图5示出了本申请实施例提出的一种语音助手与用于提供商品信息的客户端的服务端进行通信的示意图；
图6示出了本申请实施例提出的一种卡片的示意图；
图7示出了本申请实施例提出的一种多卡片展示的示意图；
图8示出了本申请实施例提出的一种卡片切换的示意图；
图9示出了本申请实施例提出的一种卡片展示商品详细信息的示意图；
图10示出了本申请另一实施例提出的一种信息推荐方法的流程图；
图11示出了本申请再一实施例提出的一种信息推荐方法的流程图；
图12示出了本申请又一实施例提出的一种信息推荐方法的流程图；
图13示出了本申请实施例提出的一种语音信息处理装置的结构框图；
图14示出了本申请另一实施例提出的一种语音信息处理装置的结构框图；
图15示出了本申请再一实施例提出的一种语音信息处理装置的结构框图；
图16示出了本申请的用于执行根据本申请实施例的信息推荐方法的电子设备的结构框图；
图17是本申请实施例的用于保存或者携带实现根据本申请实施例的信息推荐方法的程序代码的存储单元。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
随着语音识别技术的发展，类似于智能手机、平板电脑以及计算机等电子设备都配置有智能语音助手。比如苹果的Siri、三星的Bixby、Google Assistant、Amazon Alex等。语音助手可以看做是一个智能应用，用户通过与语音助手的智能对话与即时问答的智能交互，从而可以帮助用户解决一些实际的问题或者替代用户对电子设备进行操作。例如，在一个相关的场景中，电子设备的语音助手在检测到用户输入有“帮我打开百度地图”时，电子设备可以识别到用户的意图是使用百度地图这个应用程序，从而就可以出发百度地图启动。在另一个相关的场景中，电子设备的语音助手在检测到用户输入有“附近哪里有停车场”时，电子设备可以识别出用户是期望查找一定范围内的停车场，那么电子设备可以基于位置进行停车场的搜索，并将搜索结果进行展示。但是，发明人在对语音助手进行研究中发现，相关的语音助手还无法对用户输入的购物相关信息的语义进行良好的识别，或者即使能够进行响应，也无法给用户带来更好的用户体验。例如，在一种方式中，相关的语音助手在识别到用户输入我要买东西后，要么就是以“买东西”或者“东西”作为关键词进行类似搜索引擎方式进行资源搜索，然后显示所搜索的文本资料，要么就可能是直接搜索附近的商场进行展示。然而，发明人发现，相关的语音助手对于购物相关信息的响应并不是用户的真正意图，进而无法提升用户的体验也无法满足用户的实际需求。再者，发明人还发现，在直接采用相关的购物软件进行的下单的过程中，用户需要多次反复进行页面的滑动才能找到自己所需的商品，进而也会造成用户体验不佳。
因此，发明人提出了本申请中可以改善上述问题的信息推荐方法、装置、电子设备以及存储介质，通过本方法实现了用户通过语音来触发显示购物的相关信息，并且语音助手可以根据用户的画像给用户推荐匹配的目标商品信息，进而可以使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的商品，从而极大的提升了用户体验。
下面将结合附图具体描述本申请的各实施例。
请参阅图1，本申请实施例提供的一种信息推荐方法，应用于语音助手，所述方法包括：
步骤S110：所述语音助手在启动后开始接收语音信息。其中，可以理解的是，语音助手可以是一个独立运行在电子设备中的应用程序。也可以是配置在某一个应用程序中的组件。在用户使用过程中，用户可以通过触控电子设备的物理按键来触发语音助手启动，也可以通过触控电子设备所显示的虚拟按键来触发语音助手启动。
例如，作为一种方式，在电子设备设置有HOME键的情况下，电子设备可以在预先配置长按HOME 键或者双击HOME键就触发关联的目标应用程序启动，或者长按HOME键或者双击HOME键就触发关联的目标应用程序中的某个组件启动的情况下，将关联的目标应用程序或者目标应用程序中的某个组件配置为语音助手，从而实现长按HOME键或者双击HOME键就触发语音助手启动。而作为另外一种方式，电子设备配置有触控显示屏，那么电子设备可以在系统的桌面或者某个应用程序中配置有触发语音助手启动的入口。在桌面配置语音助手入口的这种情况下，入口可以为名称为语音助手的桌面应用程序图标，而在某个应用程序中配置有触发语音助手启动的入口的这种情况下，入口为可以某个名称为语音助手的控件，例如，文本控件或者按钮控件。
当语音助手启动后，电子设备可以显示如图2所示的界面，在该界面显示以后电子设备就会触发所配置的麦克风或者其它的物理语音采集元件开始进行声音的采集，以便启动后的语音助手可以获取到所采集的语音信息。
步骤S120：当接收到语音信息后，对所述接收到的语音信息进行识别。可以理解的是，对于语音助手接受到的语音信息都还是声音信号，语音助手还需要将声音信号形式的语音信息转换为文本形式的语音信息，而这个转换过程就是对接收到的语音信息进行识别的过程。
在本申请实施例中，语音助手有多种方式来实现对所述接收到的语音信息进行识别。作为一种方式，可以预先配置第三方语音识别系统的API(Application Programming Interface，应用程序编程接口)，那么在在这种方式下，语音助手可以基于预先配置的第三方语音识别系统的API将待识别的声音信号传输给第三方进行识别，然后接收第三方返回的文本形式的语音信息。例如，可以采用微软或者谷歌提供的第三方语音识别系统的API。
作为另外一种方式，可以预先对神经网络模型进行训练，得到一个具备将声音信号形式的语音信息转换为文本形式的语音信息的模型。然后将该训练好的模型部署在一个指定的服务器或者服务集群中，进而语音助手在需要对所述接收到的语音信息进行识别的过程中，可以将接收到的声音信号形式的语音信息传输给该服务器或者服务集群中进行识别，然后再接收服务器或者服务集群所返回的识别后的文本形式的语音信息。而在另外一种方式中，语音助手可以在调用第三方语音识别系统的API进行识别，和传输给指定的服务器或者服务集群进行识别进行实时的选择，以便增强识别的灵活性。
在这种方式中，可选的，语音助手可以根据当前的网络状态确定进行哪种形式的识别。可以理解的是，直接通过WIFI热点接入到网络相比通过移动通信基站接入网络而言通信过程会更加的稳定，那么语音助手可以在识别到当前是通过WIFI方式接入网络的情况下，调用第三方语音识别系统的API进行识别，而在识别到当前是通过移动通信基站接入网络的情况下，传输给指定的服务器或者服务集群进行识别。再者，语音助手还可以通过识别成功率进行识别方式的切换。可以理解的是，不同用户的发音习惯或者说话方式都会有所差别，那么即使是对于同一种识别方式，也会因为用户自身的发音习惯或者说话方式而造成识别出现不同的结果。那么在这种情况下，语音助手可以根据用户自身的习惯以及结合识别的成功率进行识别方式的切换。其中，语音助手可以在检测到用户重复对相似的声音信号进行识别的情况下，判断识别出现失败。那么语音助手可以在识别到采用某种识别方式出现指定次数失败后，转而切换为另一种识别方式。例如，若语音助手开始采用的是调用第三方语音识别系统的API进行识别，检测到连续识别了三次相似的声音信号(指定次数为3)，那么就判定转而切换为传输给该服务器或者服务集群中进行识别。需要说明的是，其中相似的声音信号可以通过判断两个声音信号的误差能量来进行判断。
步骤S130：若识别到所述接收到的语音信息中未包括有购物相关信息时，则结束当次流程。
步骤S131：若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息。
其中，购物相关信息包括：我要买东西、我要购物、我要在拼多多上购物等。可以理解的是，语音助手是在识别到一些特定的信息后，才会触发去获取目标商品提供平台以及商品信息。例如，待推荐的目标商品信息。而其中的特定的信息包括购物相关信息，该购物相关信息可以包括“我要买东西”、“买东西”或者“购物”等。那么在这种方式下，当语音助手识别到接收到的语音信息中包括有购物相关信息时，就判定用户是希望购物，进而就会去获取待推荐的目标商品信息。
其中，对于购物相关信息的配置方式有多种。作为一种方式，可以在语音助手安装时就默认配置几种经过统计后得到的常见的购物相关信息。例如，前述的“我要买东西”、“买东西”或者“购物”等。再者，作为另外一种方式，还可以由用户根据自己的需求进行配置。随着用户需求的变化，更多的用户期望采用更具有个性化的方式进行电子设备的控制。例如，有的用户喜欢说“我要买点东东”或者喜欢说“我手痒了”等，那么为了使得语音助手可以适应不同语言表达习惯的用户，可以配置由用户来进行购物相关信息的配置。
例如，如图3所示，在图3所示的购物语言设置界面98中包括有购物相关信息添加控件97以及已添加购物相关信息的展示控件96。进而在用户点击购物相关信息添加控件97后可以添加新的购物相关信 息。并且在添加过程中除了可以以文本形式添加后，还可以同时以声音信号的方式添加。例如，当用户点击购物相关信息添加控件97触发用户录入声音形式的购物相关信息，例如在用户输入的为“我要买东东”后，除了会在图4所示的购物相关信息的展示控件96展示文本形式的“我要买东东”后，还会同时存储“我要买东东”对应的声音信号。那么在这种方式下，语音助手在接收到语音信息后，为了提升最终的反馈效果，可以先直接比对所接收到的声音信号和预先存储的声音信号，可以理解的是，在比对声音信号的过程中可以采用前述的比较信号相似的方式，来确定所接收到的声音信号和预先存储的声音信号是否有相似匹配的，若有，则可以直接获取目标商品信息，而不用再进行后续的语言到文本的转换识别，从而提升信息反馈的效率。
而在本申请实施例中语音助手有多种方式来获取到待推荐的目标商品信息。作为一种方式，在目标商品信息提供平台为用于提供商品信息的客户端，在这种方式下语音助手可以基于与用于提供商品信息的客户端之间的数据接口来获取待推荐的目标商品信息。在这种方式下，语音助手会向所述用于提供商品信息的客户端发送信息获取请求，所述信息获取请求用于触发所述用于提供商品信息的客户端按照指定规则获取待推荐的目标商品信息；接收所述用于提供商品信息的客户端返回待推荐的目标商品信息。如图5所示，在这种方式下，语音助手会先进行通信通道95将信息获取请求发送到用于提供商品信息的客户端，用于提供商品信息的客户端可以先查询本地是否有缓存的目标商品信息，如果有就直接返回给语音助手，若检测到没有缓存的目标商品信息，就基于通信通道94向服务端发送获取目标商品信息的请求，进而再依次通过通信通道94以及通信通道95返回给语音助手。可以理解的是，这里的用于提供商品信息的客户端为可以用于独立完成购物订单生成以及下单的客户端，类似于拼多多客户端或者淘宝客户端。作为另外一种方式，向用于提供商品信息的客户端所对应的服务端发送信息获取请求，所述信息获取请求用于触发所述服务端按照指定规则获取目标商品信息；接收所述服务端返回的目标商品信息。例如，请再次参阅图5，在这种方式下，语音助手就会通过通信通道93直接向服务端发送信息获取请求，进而依然是通过通信通道93将待推荐的目标商品信息返回给语音助手。而在再一种方式中，语音助手可以将信息获取请求通过用于提供商品信息的客户端转发给服务器，而服务器则是通过直接将待推荐的目标商品信息返回给语音助手，而不用再通过用于提供商品信息的客户端进行转换，进而提升信息传输速率。可以理解的是，对于语音助手所在的电子设备以外的设备是通过应用程序所占用的端口号来区分应用程序的。例如，浏览器客户端占用80端口，语音助手占用8080端口，那么若返回的信息指向的为8080端口，那么电子设备就会知道这个信息是返回给语音助手的。在这种方式中，语音助手在生成信息获取请求中添加语音助手所占用的端口号，进而当服务端在生成返回的信息时，就将返回信息中添加语音助手的端口号，以便该信息可以被直接发送给语音助手。
需要说明的是，在本实施例中所述的待推荐的目标商品信息可以包括基于多个维度分别获取距离用户当前位置最近的商家的商品信息，也可以是配送范围与用户匹配且好评度较高的几个商家的商品信息，还可以是直接适配用户历史下单商品的商家的商品信息，当然，还可以是上述几种规则混合后的商品信息。在本实施例中，具体是何种指定的规则不做具体限定，可以是上述多种规则中的一个或者多个混合采用。并且，也可以定期更换所采用的指定的规则。
步骤S140：显示卡片，并在所述卡片中显示所述目标商品信息。在获取待推荐的目标商品信息后，可以将目标商品信息显示在如图6所示的卡片92中。其中，目标商品信息可以包括商户名称、评分信息、销售量以及商品类型等。当然，作为一种方式，语音助手可以检测所述所述目标商品信息的数量；若检测到所述目标商品信息的数量为多个时，显示多个卡片，其中每个卡片对应显示一个目标商品信息。例如，如图7所示，在识别到目标商品信息有3个的情况下，可以分别显示3个卡片92a、92b以及92c来分别显示这3个目标商品信息。此外，若识别到目标商品信息的数量无法直接在同一个界面中显示，可以先仅显示部分的目标商品信息，进而在检测到用户朝向屏幕上侧滑动后，加载更多的目标商品信息进行显示，并同时隐藏部分之前已经显示过的目标商品信息。例如，在图8所示的界面中，检测到用户朝向箭头所示的方向滑动屏幕后，会将排位最靠近箭头所示方向的卡片92a进行隐藏，而加载新的卡片92e进行显示。可以理解的是，所述显示卡片，并在所述卡片中显示所述目标商品信息的步骤之后还包括：获取从所述目标商品信息中确定的待下单的商品信息；基于所述待下单的商品信息生成订单。
在显示目标商品信息后，用户可以进一步的进行操控，进而使得语音助手显示更多的信息，以便用户选择所需的商品下单。其中，作为一种方式，语音助手在获取到用户所选择的目标商户信息后，可以将选择的目标商户信息发送给目标客户端，所述选择的目标商户信息用于触发所述目标客户端生成订单信息，并显示所生成的订单信息。可以理解的是，在这种方式下，语音助手会触发目标客户端切换到前台显示，进而将触发所述目标客户端生成订单信息，并显示所生成的订单信息。当然，在订单生成后，所述方法还可以包括：检测到所述订单支付后，将所述订单发送给用于提供商品信息的客户 端的服务端，并接收所述服务端返回的订单执行情况。其中，在支付过程中，语音助手支持调用第三方支付服务商进行支付，例如，微信支付或者支付宝支付，也可以支持调用语音助手本身所对应配置的支付服务器进行支付。例如，作为一种方式，若检测到作用于所述卡片的指定触控操作后，显示所述目标商品信息的详细信息，所述详细信息包括所述目标商品信息对应的对个规格。其中，可选的，若检测到作用于所述卡片的延指定方向的滑动操作后，在所述卡片中显示所述目标商品信息的详细信息。例如，如图9所示，语音助手检测到卡片92a上有朝向箭头所示方向的滑动操作后，就可以显示右侧图中所示的具体的规格A、规格B以及规格C等信息。
在本实施例中，所述显示卡片，并在所述卡片中显示所述目标商品信息的步骤之后还包括：获取从所述目标商品信息中确定的待下单的商品信息；基于所述待下单的商品信息生成订单。所述基于所述待下单的商品信息生成订单的步骤之后还包括：检测到所述订单支付后，将所述订单发送给所述服务端，并接收所述服务端返回的订单执行情况。
需要说明的是，显示卡片并在卡片中显示目标商品信息后，检测到作用于卡片中某个商品信息上的指定触控操作后，语音助手可以触发所在的电子设备启动与目标商品信息提供平台对应的客户端启动，并在该启动的客户端中加载用户所触控的商品信息的详细信息。
可以理解的是，在触发与目标商品信息提供平台对应的客户端之前，可以先检测语音助手所在电子设备中是否安装有该客户端，在检测到未安装的情况下可以通过预先定义的与电子设备中的应用程序下载客户端之间的接口，来获取目标商品信息提供平台对应的客户端的下载页面，并在语音助手中显示一个新的卡片，并在该新的卡片中加载目标商品信息提供平台对应的客户端的下载页面，从而使得即使在电子设备未安装目标商品信息提供平台对应的客户端的情况下，用户也不需要再操作电子设备进行页面切换或者应用程序的切换就可以直接在语音助手中下载所需的客户端，进而提升了用户的体验。其中，语音助手与应用程序下载客户端之间可以通过进程间通信的方式实现数据交互。
其中，对于应用程序下载客户端本身的页面显示方式不同，所传输给语音助手的下载页面数据会有对应的不同。
作为一种方式，若应用程序下载客户端为基于Client/Server架构的情况下，应用程序下载客户端中的界面为预先就配置在电子设备中的，只是在运行过程中向对应的服务器请求数据并展示在界面中即可，即在这种情况下界面包括本地的界面数据以及从服务器请求而来的动态数据。那么这种情况下，语音助手是无法直接显示客户端存储在本地的界面数据的，那么适应性的，语音助手可以直接在前述新的卡片中生成一个绑定有目标商品信息提供平台对应的客户端的标识的控件，而该标识为从应用程序下载客户端中请求得到。那么在这种方式下，用户在点击该绑定有目标商品信息提供平台对应的客户端的标识的控件后，语音助手会将所需下载的客户端的标识传输给应用程序下载客户端，触发应用程序下载客户端来执行客户端的下载并安装。作为另外一种方式，若应用程序下载客户端为基于BS架构的情况下，应用程序下载客户端中的所显示的界面都是直接从服务端获取的，那么所从服务端请求回来的页面数据也都是基于html的数据，所以可以直接传输给语音助手进行渲染显示。那么在这种方式下，若语音助手识别到应用程序下载客户端为基于BS架构，可以直接向该应用程序下载客户端请求目标商品信息提供平台对应的客户端的下载页面，并在新的卡片中渲染显示该下载页面。当用户点击该下载界面触发下载后，语音助手会直接向服务端请求客户端数据以完成下载安装，而不会再通过应用程序下载客户端进行下载。通过语音助手对于应用程序下载客户端的架构的识别，可以使得语音助手能够灵活多样的选择下载界面的生成方式，提升了下载的适配性以及成功率，进而也提升了用户体验。
本申请提供的一种信息推荐方法，在语音助手在启动后开始接收语音信息后，当接收到语音信息时，对所述接收到的语音信息进行识别，若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息，然后显示卡片，并在所述卡片中显示所述目标商品信息。从而通过本方法实现了用户通过语音来触发显示购物的相关信息，并且语音助手可以根据用户的画像给用户推荐匹配的目标商品信息，进而可以使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的商品，从而极大的提升了用户体验。
请参阅图10，本申请实施例提供的一种信息推荐方法，应用于语音助手，所述方法包括：
步骤S210：所述语音助手在启动后开始接收语音信息。
步骤S220：当接收到语音信息后，对所述接收到的语音信息进行识别。
步骤S230：若识别到所述接收到的语音信息中未包括有购物相关信息时，结束当次流程。
步骤S231：若识别到所述接收到的语音信息中包括有购物相关信息时，获取所述语音助手绑定用户使用过的商品信息提供平台的历史操作行为。
步骤S240：基于所述历史操作行为从用户使用过的商品信息提供平台中确定目标商品信息提供平台。作为一种方式，所述历史操作行为包括多个行为参数，所述基于所述历史操作行为从用户使用过的商品信息提供平台中确定目标商品信息提供平台的步骤包括：基于使用过的商品信息提供平台各自对应的多个行为参数，计算得到每个使用过的商品信息提供平台的评分；将评分满足指定条件的使用过的商品信息提供平台作为目标商品信息提供平台。其中，多个行为参数可以包括使用时长以及点击次数等。在这种情况下，语音助手就可以基于每个商品信息提供平台各自的使用时长以及点击次数对商品信息提供平台进行评分。
而其中的评分方式，可以有多种。作为一种方式，每个行为参数对应一个分值，当检测到有对应的行为被触发以后，就可以对应更新触发行为对应的行为参数的分值。例如，语音助手可以实时获取电子设备当前所运行的客户端，进而在某个商品信息提供平台的客户端在运行后可以统计其运行时间，将其运行时间作为使用时长，进而更新使用时长所对应的分值。再例如，当语音助手检测到当前前台运行的应用程序为某个商品信息提供平台的客户端时，可以实时统计当前屏幕被点击的次数作为该前台运行的商品信息提供平台的客户端的点击次数，进而更新点击次数这个参数对应的分值。最后，直接将每个行为参数对应的分值相加就是某个商品信息提供平台的评分。例如，对于商品信息提供平台A，语音助手统计得到商品信息提供平台A的使用时长这个参数的分值为a，而点击次数这个参数的分值为b，那么语音助手就可以计算得到商品信息提供平台A的评分为a+b。作为另外一种方式，每个所述行为参数对应有各自的权重，所述基于使用过的商品信息提供平台各自对应的多个行为参数，计算得到每个使用过的商品信息提供平台的评分的步骤包括：将每个行为参数对应的评分与各自的权重相乘得到每个使用过的商品信息提供平台对应的多个参数评分；将每个使用过的商品信息提供平台对应的多个参数评分相加得到每个使用过的商品信息提供平台对应的评分。在这种方式中，语音助手不会直接将每个行为参数对应的分值相加得到某个商品信息提供平台的评分，而是会将每个行为参数对应的分值与权重相乘后的分数再相加，进而得到某个商品信息提供平台的评分。例如，对于商品信息提供平台A，语音助手统计得到商品信息提供平台A的使用时长这个参数的分值为a，而点击次数这个参数的分值为b，而使用时长的权重为0.6，点击次数的权重为0.4，那么最终得到的评分为0.6*a+0.4*b。
需要说明的是，在前述直接将每个行为参数对应的分值相加而得到商品信息提供平台对应的评分这种方式中，评分算法较为简便，可以更加快速的得到商品信息提供平台的评分。而在后续引入行为参数的权重的这种方式中，会因为权重的变化而影响某个行为参数的重要性，从而有利于灵活的调整每个行为参数的重要程度，使得最终的评分可以有更好的灵活性以及实时性。具体的，可以理解的是使用时长是通过客户端的运行时间来体现的，表征的是用户使用习惯，对于运行时长更长的商品信息提供平台是用户更习惯使用的商品信息提供平台，而点击次数是用户在使用过程中操作的频率，表征的是商品信息提供平台所能提供的商品信息的丰富程度，点击次数越多表征所能提供的信息越丰富。那么如果语音助手识别到当前更适合适配用户使用习惯的商品信息提供平台的情况下，可以增大使用时长对应的权重，而若语音助手识别到更适合适配能提供更多商品信息的平台的情况下，可以增加点击次数对应的权重。例如，语音助手在识别到用户所期望购买的商品后，识别到该商品是一个常见商品，那么就可以以用户的使用习惯为优先考虑，因为对于常见商品，各个商品信息提供平台都可以提供对应的信息。而当语音助手识别到该商品不是常见商品时，就可以可以提供更丰富的商品信息为优先考虑，以便可以更快以及更加便捷的让用户找到自己所需的商品。可以理解的是，语音助手可以通过商品信息提供平台所提供的商品信息接口来获取每个商品的种类，将种类数量较多(多于指定阈值)的作为常见商品，而将种类数量较少(少于指定阈值)的作为非常见商品。
步骤S250：向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息。
步骤S260：显示卡片，并在所述卡片中显示所述目标商品信息。作为一种方式，在获取所述语音助手绑定用户使用过的商品信息提供平台的历史操作行为的步骤之前还包括：识别所述语音信息中是否还包括有商品信息提供平台的标识，若否，执行所述获取所述语音助手绑定用户使用过的商品信息提供平台的历史操作行为，若是，将所述语音信息中还包括的商品信息提供平台作为目标商品信息提供平台。可以理解的是，用户有时候会有自己的明确的购物平台目标，那么用户在触发语音助手搜索商品时，就会发出自己所期望的购物平台的信息。例如，用户发出的语音信息为“我要在拼多多上买吃的”，那么其中的“拼多多”就可以被会被识别为所期望的购物平台的信息，也就是前述的语音信息中还包括的商品信息提供平台的标识。
本申请提供的一种信息推荐方法，通过本方法实现了用户通过语音来触发显示购物的相关信息，并且语音助手可以根据用户的画像给用户推荐匹配的目标商品信息，进而可以使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的 商品，从而极大的提升了用户体验。并且，在确定目标商品信息提供平台的过程中，可以根据用户的历史操作行为来为用于确定一个最匹配的商品信息提供平台作为目标商品信息提供平台，以便可以提升用户体验，进而可以使得能够更加快速准确的展示用户自己习惯的购物平台中的与用户需求匹配的商品信息。
请参阅图11，本申请实施例提供的一种信息推荐方法，应用于语音助手，所述方法包括：
步骤S310：所述语音助手在启动后开始接收语音信息。
步骤S320：当接收到语音信息后，对所述接收到的语音信息进行识别。
步骤S320：若识别到所述接收到的语音信息中包括有购物相关信息时，结束当次流程。。
步骤S331：若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息。
步骤S340：显示卡片，并在所述卡片中显示所述目标商品信息。
步骤S350：当检测到更换商品信息的指示后，从所述使用过的商品信息提供平台中确定一商品信息提供平台获取目标商品信息，且每次确定的商品信息提供平台不同。
作为一种方式，在语音助手确定目标商品信息提供平台，并从该目标商品信息提供平台获取目标商品信息进行展示后，有可能所展示的商品信息不是用户当次用需要的，而不同的商品信息提供平台所能提供的商品会有不同，那么即使是相同的搜索内容，不同的商品信息提供平台所提供的商品信息也会有所区别。那么在语音助手统计到用户所使用过的商品信息提供平台有多个的情况下，可以让用户再触发更换平台进行商品信息的搜索。
步骤S360：在所述卡片中展示从所述确定的商品信息提供平台获取的目标商品信息。
步骤S370：若检测到有订单生成后，检测所下单的商品是否属于所述目标商品信息提供平台对应的目标商品。
作为一种方式，语音助手在获取到商品信息提供平台返回的目标商品信息后，会将该目标商品信息与商品信息提供平台对应的存储在本地，以便标识每个商品信息所属的提供平台，也便于语音助手可以识别当前所展示的商品信息所述的提供平台。
步骤S380：若不属于，获取待处理行为参数，所述待处理行为参数为多个行为参数中所对应的权重最大的一个行为参数。可以理解的是，对应的权重的值最大的一个行为参数往往会对最终的评分有更大的影响。但是，在用户最终下单的商品不属于最初的目标商品信息提供平台所提供的商品的情况下，语音助手可以判定目标商品平台未能提供用户切实所期望的商品，那么就可以降低影响本次确定目标商品信息提供平台最大的行为参数的权重，即影响本次确定目标商品信息提供平台最大的行为参数作为待处理行为参数。
步骤S390：降低所述待处理参数对应的权重，并提升多个行为参数中除所述待处理行为参数外的行为参数的权重。作为一种方式，步骤S390中的对待处理参数的权重的降低，以及对多个行为参数中除所述待处理行为参数外的行为参数的权重的提升可以是普遍性的，也可以是有针对性的。
在有针对性的这种情况下，语音助手在检测到当次的购物相关信息与最近一次用户最终下单产品不属于目标商品信息提供平台所提供的商品的情况下的购物信息相同时，采用多个行为参数更新后的权重来计算得到当次的目标商品信息提供平台，其中，多个行为参数更新后的权重为语音助手最近一次在检测到用户最终下单产品不属于目标商品信息提供平台所提供的商品的情况下更新的多个行为参数的权重。
其中，作为一种方式，所述降低所述待处理参数对应的权重，并提升多个行为参数中除所述待处理行为参数外的行为参数的权重的步骤之前包括：
检测所述向目标商品信息提供平台获取的目标商品信息对应的商品中是否有与用户下单商品相同的商品；若无，执行所述降低所述待处理参数对应的权重，并提升多个行为参数中除所述待处理行为参数外的行为参数的权重。若有则可以按照与相似程度对应的比例来降低所述待处理行为参数外的行为参数的权重。其中相似程度越高，那么待处理行为参数外的行为参数的权重则所要降低的值就越低。其中，在目标商品信息提供平台获取的目标商品信息对应的商品中有与用户下单商品相同的商品的情况下所降低的权重的最大幅度低于在目标商品信息提供平台获取的目标商品信息对应的商品中没有与用户下单商品相同的商品的情况下所降低的权重的最大幅度。
例如，若预先配置通过得分来评价相似程度，其中得分越高，表征越相似。例如，那么最初的目标商品信息提供平台所提供的目标商品信息中包括商品A、商品B、商品C以及商品D，而用户最终购买的为其他商品商品信息提供平台中的商品Z，而其中商品Z与商品B是相似的，且当前目标商品信息提供平台对应的多个行为参数中，使用时长的权重为0.6，点击次数的权重为0.4，若 商品Z与商品B的相似程度为3分，那么使用时长(待处理行为参数)的权重就会从0.6降低到0.5，而若商品Z与商品B的相似程度为5分，那么使用时长(待处理行为参数)的权重就会从0.6降低到0.58。
其中，商品的相似程度可以通过商品的多个属性来进行比对，相同属性越多评分越高。其中的多个属性包括，商品名称、商品规格、商品价格以及预估配送时间等。
通过上述的权重更新方式，可以使得语音助手能够根据实时数据修正最终为用户所推荐的目标商品信息提供平台的准确性，
本申请提供的一种信息推荐方法，通过本方法实现了用户通过语音来触发显示购物的相关信息，并且语音助手可以根据用户的画像给用户推荐匹配的目标商品信息，进而可以使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的商品，从而极大的提升了用户体验。并且，在本实施例中，在显示目标商品平台所提供的目标商品信息后，用户还可以继续选择显示其他商品提供平台所提供的目标商品信息，进而实现可以便捷性的在多个商品提供平台之间进行切换，同时也便于用户直接在语音助手中在一次语音信息查询反馈中就可以展示多个商品信息提供平台的目标商品信息。
请参阅图12，本申请实施例提供的一种信息推荐方法，应用于语音助手，所述方法包括：
步骤S410：所述语音助手在启动后开始接收语音信息。
步骤S420：当接收到语音信息后，对所述接收到的语音信息进行识别。
步骤S421：若识别到所述接收到的语音信息中未包括有购物相关信息时，结束当次流程。
步骤S430：若识别到所述接收到的语音信息中包括有购物相关信息时，获取存储的预先计算得到的用户画像参数，所述用户画像参数表征用户的感兴趣商品的类别。
步骤S431：基于所述用户画像参数向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息。
可以理解的是，用户使用电子设备的过程中，可能会利用电子设备访问互联网，或者使用音乐播放器等媒体，或者通过新闻客户端浏览新闻，再或者通过购物客户端进行网购等。而对于用户的这个操作行为都可以反映出用户的一些个人喜好。例如，如果检测到用户经常在购物客户端购物打折商品，那么可以可以判定用户在一定程度上比较在意物品的价格，那么在推荐商品信息时，就尽可能的推荐打折的商品，这样有利于用户提升推荐转化率。再例如，若用户经常浏览一些奢侈商品的推荐的文章，那么可以判定用户对于商品品质有较高的最求，那么就可以给用户推荐一些有特色且品质较高的商品。
步骤S440：显示卡片，并在所述卡片中显示所述目标商品信息。
其中，作为一种方式，所述获取存储的预先计算得到的用户画像参数的步骤之前还包括：周期性的获取所述语音助手绑定用户访问网络资源的历史操作行为；基于所述用户访问网络资源的历史操作行为，计算得到与用户匹配的兴趣类别作为用户画像参数。
其中，可选的，所述基于所述用户访问网络资源的历史操作行为，计算得到与用户匹配的兴趣类别作为用户画像参数的步骤包括：
获取多个行为维度中与所述用户访问网络资源的历史操作对应的目标行为维度。
可选的，所述多个行为维度包括媒体访问维度、新闻维度、消费记录维度以及网页浏览维度中的至少两个。可以理解的是，在本实施例中，语音助手可以对用户的每次行为进行监测并进行识别。例如，在检测到用户购买了一件打折商品操作行为后，那么就会判定目标行为维度为消费记录维度。再例如，当检测到用户打开了标题为“经典美食推荐”的网页后，就会判定目标行为维度为网页浏览维度。
获取目标兴趣类别，所述目标兴趣类别为所述目标行为维度对应的多个兴趣类别中与所述用户访问网络资源的历史操作行为对应的兴趣类别，其中，每个行为维度所对应的多个兴趣类别相同。
可选的，每个行为维度所对应的多个兴趣类别相同。具体的，每个行为维度对应的多个兴趣类别包括价格类、便捷性类以及口味偏好类中至少两个。那么在获取到目标行为维度后，可以进一步的获取目标兴趣类别。所述目标兴趣类别为所述目标行为维度对应的多个兴趣类别中与所述用户历史操作行为对应的兴趣类别。例如，在检测到用户购买了一件打折商品操作行为后，那么不仅会判定目标行为维度为消费记录维度，而且会进一步的判定目标兴趣类别为价格类。再例如，在检测到用户打开了标题为“附近经典美食推荐”的网页后，不仅会判定目标行为维度为网页浏览维度，还会进一步的判定目标兴趣类别为便捷类。
增加所述目标兴趣类别的评分。可以理解的是，对于每个行为维度的多个兴趣类别都可以对应配置评分，其中，评分越高表征用户越发的关注。那么在确定当次操作行为所对应的目标兴趣类别后，就可以增加所述目标兴趣类别的评分。例如，可以每次增加1分或者2分。基于每个行为维度所对应的多个兴趣类别的评分，计算得到与用户匹配的兴趣类别作为用户画像参数。需要说明的是， 语音助手可以在每增加某一个维度的某一个兴趣类别的评分后，就开始计算与用户匹配的兴趣类别作为用户画像参数，也可以是周期性的算与用户匹配的兴趣类别作为用户画像参数。而在计算过程中，作为一种方式，所述基于每个行为维度所对应的多个兴趣类别的评分，计算得到与用户匹配的兴趣类别作为用户画像参数的步骤包括：计算得到每个所述兴趣类别的多个中间值，所述多个中间值为多个行为维度中同一兴趣类别的评分各自乘以所属行为维度的权重的值；将每个兴趣类别的多个中间值求和得到每个兴趣类别的总评分值；将总评分值排序满足目标条件的兴趣类别作为与用户匹配的兴趣类别；将所述与用户匹配的兴趣类别作为用户画像参数。下面再通过一个实例来对上述内容进行说明。
例如，在某一次的计算过程中，行为维度包括网页浏览维度、新闻维度以及消费记录维度。每个行为维度均对应价格类、便捷性类以及口味偏好类着几个兴趣类别。
其中，网页浏览维度的权重为0.5，新闻维度为权重为0.2，消费记录维度的权重为0.3。而每个维度对应的兴趣类别的评分如下表所示。
Figure PCTCN2019087665-appb-000001
那么就可以计算得到价格类的中间值包括0.5、0.4以及1.5，进而得到价格类的总评分值为2.4。计算得到便捷性类的中间值包0.5、0.6以及0.9，进而得到便捷性类的总评分值为2.0。计算得到口味偏好类的中间值包0.5、0.8以及0.6，进而得到便捷性类的总评分值为1.9。那么在目标条件为排序靠前2位的兴趣类别作为与用户匹配的兴趣类别的情况下，就可以计算得到与用户匹配的兴趣类别包括价格类以及便捷性类。
本申请提供的一种信息推荐方法，通过本方法实现了用户通过语音来触发显示购物的相关信息，并且语音助手可以根据用户的画像给用户推荐匹配的目标商品信息，进而可以使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的商品，从而极大的提升了用户体验。并且在本申请实施例中，可以根据用户的画像来为用户确定目标商品信息，进而提升了商品推荐的准确性以及适配性。
请参阅图13，本申请实施例提供的一种信息推荐装置500，所述装置500包括：语音信息接收单元510，用于在所述信息推荐装置启动后开始接收语音信息。语音识别单元520，用于当接收到语音信息后，对所述接收到的语音信息进行识别。商品信息获取单元530，用于若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息。作为一种方式，商品信息获取单元530，具体用于获取所述语音助手绑定用户使用过的商品信息提供平台的历史操作行为；基于所述历史操作行为从用户使用过的商品信息提供平台中确定目标商品信息提供平台；向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息。其中，在一种方式中，所述历史操作行为包括多个行为参数。在这种方式下，商品信息获取单元530，具体用于基于使用过的商品信息提供平台各自对应的多个行为参数，计算得到每个使用过的商品信息提供平台的评分；将评分满足指定条件的使用过的商品信息提供平台作为目标商品信息提供平台。在一种方式中，每个所述行为参数对应有各自的权重。那么在这种方式下，商品信息获取单元530，具体用于将每个行为参数对应的评分与各自的权重相乘得到每个使用过的商品信息提供平台对应的多个参数评分；将每个使用过的商品信息提供平台对应的多个参数评分相加得到每个使用过的商品信息提供平台对应的评分。作为一种方式，商品信息获取单元530，用于当语音识别单元520识别到所述语音信息中还包括有商品信息提供平台的标识的情况下，将所述语音信息中还包括的商品信息提供平台作为目标商品信息提供平台。信息显示单元540，用于显示卡片，并在所述卡片中显示所述目标商品信息。作为一种方式，如图14所示，所述装置还包括：平台切换单元550，用于检测用户触发切换商品信息提供平台的指示。在这种方式下，商品信息获取单元530，具体用于当检测到更换商品信息的指示后，从所述使用过的商品信息提供平台中确定一商品信息提供平台获取目标商品信息，且每次确定的商品信息提供平台不同。信息显示单元540，具体用于并在所述卡片中展示从所述确定的商品信息提供平台获取的目标商品信息。
在图14所示的这种方式中，还包括权重调节单元560，用于若检测到有订单生成后，检测所下单的商品是否属于所述目标商品信息提供平台对应的目标商品；若不属于，获取待处理行为参数，所述待处理 行为参数为多个行为参数中所对应的权重最大的一个行为参数；降低所述待处理参数对应的权重，并提升多个行为参数中除所述待处理行为参数外的行为参数的权重。在一种方式中，商品信息获取单元530，具体用于获取存储的预先计算得到的用户画像参数，所述用户画像参数表征用户的感兴趣商品的类别；基于所述用户画像参数向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息。
在这种方式下，如图15所示，装置500还包括画像参数计算单元570，用于周期性的获取所述语音助手绑定用户访问网络资源的历史操作行为；基于所述用户访问网络资源的历史操作行为，计算得到与用户匹配的兴趣类别作为用户画像参数。其中，画像参数计算单元570，具体用于获取多个行为维度中与所述用户访问网络资源的历史操作对应的目标行为维度；获取目标兴趣类别，所述目标兴趣类别为所述目标行为维度对应的多个兴趣类别中与所述用户访问网络资源的历史操作行为对应的兴趣类别，其中，每个行为维度所对应的多个兴趣类别相同；增加所述目标兴趣类别的评分；基于每个行为维度所对应的多个兴趣类别的评分，计算得到与用户匹配的兴趣类别作为用户画像参数。在图16所示的这种方式中，画像参数计算单元570，具体用于计算得到每个所述兴趣类别的多个中间值，所述多个中间值为多个行为维度中同一兴趣类别的评分各自乘以所属行为维度的权重的值；将每个兴趣类别的多个中间值求和得到每个兴趣类别的总评分值；将总评分值排序满足目标条件的兴趣类别作为与用户匹配的兴趣类别；将所述与用户匹配的兴趣类别作为用户画像参数。其中，所述多个行为维度包括媒体访问维度、新闻维度、消费记录维度以及网页浏览维度中的至少两个。所述多个兴趣类别包括价格类以及便捷性类。如图16所示，所述装置500还包括订单处理单元580，用于向目标客户端的服务端发送待推荐的目标商品信息获取请求，接收所述服务端返回的待推荐的目标商品信息。还用于检测到所述订单支付后，将所述订单发送给所述服务端，并接收所述服务端返回的订单执行情况。需要说明的是，本申请中装置实施例与前述方法实施例是相互对应的，装置实施例中具体的原理可以参见前述方法实施例中的内容，此处不再赘述。
下面将结合图17对本申请提供的一种电子设备进行说明。
请参阅图17，基于上述的信息推荐方法、装置，本申请实施例还提供的另一种可以执行前述信息推荐方法的电子设备200。电子设备200包括相互耦合的一个或多个(图中仅示出一个)处理器102、存储器104以及网络模块106。其中，该存储器104中存储有可以执行前述实施例中内容的程序，而处理器102可以执行该存储器104中存储的程序。其中，处理器102可以包括一个或者多个处理核。处理器102利用各种接口和线路连接整个电子设备200内的各个部分，通过运行或执行存储在存储器104内的指令、程序、代码集或指令集，以及调用存储在存储器104内的数据，执行电子设备200的各种功能和处理数据。可选地，处理器102可以采用数字信号处理(Digital Signal Processing，DSP)、现场可编程门阵列(Field－Programmable Gate Array，FPGA)、可编程逻辑阵列(Programmable Logic Array，PLA)中的至少一种硬件形式来实现。处理器102可集成中央处理器(Central Processing Unit，CPU)、图像处理器(Graphics Processing Unit，GPU)和调制解调器等中的一种或几种的组合。其中，CPU主要处理操作系统、用户界面和应用程序等；GPU用于负责显示内容的渲染和绘制；调制解调器用于处理无线通信。可以理解的是，上述调制解调器也可以不集成到处理器102中，单独通过一块通信芯片进行实现。存储器104可以包括随机存储器(Random Access Memory，RAM)，也可以包括只读存储器(Read-Only Memory)。存储器104可用于存储指令、程序、代码、代码集或指令集。存储器104可包括存储程序区和存储数据区，其中，存储程序区可存储用于实现操作系统的指令、用于实现至少一个功能的指令(比如触控功能、声音播放功能、图像播放功能等)、用于实现下述各个方法实施例的指令等。存储数据区还可以存储终端100在使用中所创建的数据(比如电话本、音视频数据、聊天记录数据)等。所述网络模块106用于接收以及发送电磁波，实现电磁波与电信号的相互转换，从而与通讯网络或者其他设备进行通讯，例如和音频播放设备进行通讯。所述网络模块106可包括各种现有的用于执行这些功能的电路元件，例如，天线、射频收发器、数字信号处理器、加密/解密芯片、用户身份模块(SIM)卡、存储器等等。所述网络模块106可与各种网络如互联网、企业内部网、无线网络进行通讯或者通过无线网络与其他设备进行通讯。上述的无线网络可包括蜂窝式电话网、无线局域网或者城域网。例如，网络模块106可以与基站进行信息交互。请参考图18，其示出了本申请实施例提供的一种计算机可读存储介质的结构框图。该计算机可读介质1100中存储有程序代码，所述程序代码可被处理器调用执行上述方法实施例中所描述的方法。计算机可读存储介质1100可以是诸如闪存、EEPROM(电可擦除可编程只读存储器)、EPROM、硬盘或者ROM之类的电子存储器。可选地，计算机可读存储介质1100包括非易失性计算机可读介质(non-transitory computer-readable storage medium)。计算机可读存储介质1100具有执行上述方法中的任何方法步骤的程序代码810的存储空间。这些程序代码可以从一个或者多个计算机程序产品中读出或者写入到这一个或者多个计算机程序产品中。程序代码1110可以例如以适当形式进行压缩。
本申请提供的一种信息推荐方法、装置、电子设备以及存储介质，在语音助手在启动后开始接收语音信息后，当接收到语音信息时，对所述接收到的语音信息进行识别，若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息， 所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息，然后显示卡片，并在所述卡片中显示所述目标商品信息。从而通过本方法实现了用户通过语音来触发显示购物的相关信息，并且语音助手可以根据用户的画像给用户推荐匹配的目标商品信息，进而可以使得用户更快的获取到自己所需的商品，进而不需要再单独启动用于购物的目标客户端，然后再通过多次的页面滑动来查找自己所需的商品，从而极大的提升了用户体验。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不驱使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (20)

  1. 一种信息推荐方法，其特征在于，应用于语音助手，所述方法包括：
    所述语音助手在启动后开始接收语音信息；
    当接收到语音信息后，对所述接收到的语音信息进行识别；
    若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息；
    显示卡片，并在所述卡片中显示所述目标商品信息。
  2. 根据权利要求1所述的方法，其特征在于，所述向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息的步骤包括：
    获取所述语音助手绑定用户使用过的商品信息提供平台的历史操作行为；
    基于所述历史操作行为从用户使用过的商品信息提供平台中确定目标商品信息提供平台；
    向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息。
  3. 根据权利要求2所述的方法，其特征在于，所述历史操作行为包括多个行为参数，所述基于所述历史操作行为从用户使用过的商品信息提供平台中确定目标商品信息提供平台的步骤包括：
    基于使用过的商品信息提供平台各自对应的多个行为参数，计算得到每个使用过的商品信息提供平台的评分；
    将评分满足指定条件的使用过的商品信息提供平台作为目标商品信息提供平台。
  4. 根据权利要求3所述的方法，其特征在于，每个所述行为参数对应有各自的权重，所述基于使用过的商品信息提供平台各自对应的多个行为参数，计算得到每个使用过的商品信息提供平台的评分的步骤包括：
    将每个行为参数对应的评分与各自的权重相乘得到每个使用过的商品信息提供平台对应的多个参数评分；
    将每个使用过的商品信息提供平台对应的多个参数评分相加得到每个使用过的商品信息提供平台对应的评分。
  5. 根据权利要求2所述的方法，其特征在于，所述获取所述语音助手绑定用户使用过的商品信息提供平台的历史操作行为的步骤之前还包括：
    识别所述语音信息中是否还包括有商品信息提供平台的标识；
    若否，执行所述获取所述语音助手绑定用户使用过的商品信息提供平台的历史操作行为。
  6. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    若是，将所述语音信息中还包括的商品信息提供平台作为目标商品信息提供平台。
  7. 根据权利要求4-6任一所述的方法，其特征在于，所述显示卡片，并在所述卡片中显示所述目标商品信息的步骤之后还包括：
    当检测到更换商品信息的指示后，从所述使用过的商品信息提供平台中确定一商品信息提供平台获取目标商品信息，且每次确定的商品信息提供平台不同；
    并在所述卡片中展示从所述确定的商品信息提供平台获取的目标商品信息。
  8. 根据权利要求4-7任一所述的方法，其特征在于，所述方法还包括：
    若检测到有订单生成后，检测所下单的商品是否属于所述目标商品信息提供平台对应的目标商品；
    若不属于，获取待处理行为参数，所述待处理行为参数为多个行为参数中所对应的权重最大的一个行为参数；
    降低所述待处理参数对应的权重，并提升多个行为参数中除所述待处理行为参数外的行为参数的权重。
  9. 根据权利要求8所述的方法，其特征在于，所述降低所述待处理参数对应的权重，并提升多个行为参数中除所述待处理行为参数外的行为参数的权重的步骤之前包括：
    检测所述向目标商品信息提供平台获取的目标商品信息对应的商品中是否有与用户下单商品相同的商品；
    若无，执行所述降低所述待处理参数对应的权重，并提升多个行为参数中除所述待处理行为参数外的行为参数的权重。
  10. 根据权利要求1-9任一所述的方法，其特征在于，所述向目标商品信息提供平台获取与所述 购物相关信息关联的待推荐的目标商品信息的步骤包括：
    获取存储的预先计算得到的用户画像参数，所述用户画像参数表征用户的感兴趣商品的类别；
    基于所述用户画像参数向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息。
  11. 根据权利要求10所述的方法，其特征在于，所述获取存储的预先计算得到的用户画像参数的步骤之前还包括：
    周期性的获取所述语音助手绑定用户访问网络资源的历史操作行为；
    基于所述用户访问网络资源的历史操作行为，计算得到与用户匹配的兴趣类别作为用户画像参数。
  12. 根据权利要求11所述的方法，其特征在于，所述基于所述用户访问网络资源的历史操作行为，计算得到与用户匹配的兴趣类别作为用户画像参数的步骤包括：
    获取多个行为维度中与所述用户访问网络资源的历史操作对应的目标行为维度；
    获取目标兴趣类别，所述目标兴趣类别为所述目标行为维度对应的多个兴趣类别中与所述用户访问网络资源的历史操作行为对应的兴趣类别，其中，每个行为维度所对应的多个兴趣类别相同；
    增加所述目标兴趣类别的评分；
    基于每个行为维度所对应的多个兴趣类别的评分，计算得到与用户匹配的兴趣类别作为用户画像参数。
  13. 根据权利要求12所述的方法，其特征在于，所述基于每个行为维度所对应的多个兴趣类别的评分，计算得到与用户匹配的兴趣类别作为用户画像参数的步骤包括：
    计算得到每个所述兴趣类别的多个中间值，所述多个中间值为多个行为维度中同一兴趣类别的评分各自乘以所属行为维度的权重的值；
    将每个兴趣类别的多个中间值求和得到每个兴趣类别的总评分值；
    将总评分值排序满足目标条件的兴趣类别作为与用户匹配的兴趣类别；
    将所述与用户匹配的兴趣类别作为用户画像参数。
  14. 根据权利要求12或13所述的方法，其特征在于，所述多个行为维度包括媒体访问维度、新闻维度、消费记录维度以及网页浏览维度中的至少两个。
  15. 根据权利要求12或13所述的方法，其特征在于，所述多个兴趣类别包括价格类以及便捷性类。
  16. 根据权利要求1所述的方法，其特征在于，所述显示卡片，并在所述卡片中显示所述目标商品信息的步骤之后还包括：
    获取从所述目标商品信息中确定的待下单的商品信息；
    基于所述待下单的商品信息生成订单。
  17. 根据权利要求16所述的方法，其特征在于，所述获取待推荐的目标商品信息的步骤包括：
    向目标客户端的服务端发送待推荐的目标商品信息获取请求，接收所述服务端返回的待推荐的目标商品信息；
    所述基于所述待下单的商品信息生成订单的步骤之后还包括：
    检测到所述订单支付后，将所述订单发送给所述服务端，并接收所述服务端返回的订单执行情况。
  18. 一种信息推荐装置，其特征在于，所述装置包括：
    语音信息接收单元，用于在所述信息推荐装置启动后开始接收语音信息；
    语音识别单元，用于当接收到语音信息后，对所述接收到的语音信息进行识别；
    商品信息获取单元，用于若识别到所述接收到的语音信息中包括有购物相关信息时，向目标商品信息提供平台获取与所述购物相关信息关联的待推荐的目标商品信息，所述目标商品信息为与所述语音助手绑定用户的用户画像匹配的商品信息；
    信息显示单元，用于显示卡片，并在所述卡片中显示所述目标商品信息。
  19. 一种电子设备，其特征在于，包括一个或多个处理器以及存储器；
    一个或多个程序被存储在所述存储器中并被配置为由所述一个或多个处理器执行以实现权利要求1-17任一所述的方法。
  20. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有程序代码，其中，在所述程序代码被处理器运行时执行权利要求1-17任一所述的方法。
PCT/CN2019/087665 2019-05-20 2019-05-20 信息推荐方法、装置、电子设备以及存储介质 WO2020232615A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/087665 WO2020232615A1 (zh) 2019-05-20 2019-05-20 信息推荐方法、装置、电子设备以及存储介质
CN201980090665.7A CN113366524B (zh) 2019-05-20 2019-05-20 信息推荐方法、装置、电子设备以及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/087665 WO2020232615A1 (zh) 2019-05-20 2019-05-20 信息推荐方法、装置、电子设备以及存储介质

Publications (1)

Publication Number Publication Date
WO2020232615A1 true WO2020232615A1 (zh) 2020-11-26

Family

ID=73459275

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/087665 WO2020232615A1 (zh) 2019-05-20 2019-05-20 信息推荐方法、装置、电子设备以及存储介质

Country Status (2)

Country Link
CN (1) CN113366524B (zh)
WO (1) WO2020232615A1 (zh)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112492518A (zh) * 2020-12-09 2021-03-12 深圳市欢太科技有限公司 卡片确定方法、装置、电子设备及存储介质
CN112905148A (zh) * 2021-03-12 2021-06-04 拉扎斯网络科技（上海）有限公司 一种语音播报的控制方法和装置，存储介质和电子设备
CN113158056A (zh) * 2021-04-27 2021-07-23 口碑(上海)信息技术有限公司 推荐语的生成方法及装置
CN113239268A (zh) * 2021-04-29 2021-08-10 佛山科学技术学院 一种商品推荐方法、装置及系统
CN113327134A (zh) * 2021-06-16 2021-08-31 北京百度网讯科技有限公司 商品信息推荐方法及装置、电子设备和介质
CN113506152A (zh) * 2021-07-08 2021-10-15 四川新龟科技有限公司 一种商品下单方法、装置、设备及存储介质
CN113592530A (zh) * 2021-06-24 2021-11-02 青岛海尔科技有限公司 用于业务提供方的推荐方法、装置及电子设备
CN113902466A (zh) * 2021-09-09 2022-01-07 广景视睿科技（深圳）有限公司 一种无人商店交互方法、无人商店及存储介质
CN114327349A (zh) * 2021-12-13 2022-04-12 青岛海尔科技有限公司 智能卡片的确定方法及装置、存储介质、电子装置
CN116452303A (zh) * 2023-06-14 2023-07-18 深圳市诚识科技有限公司 基于大数据的电子商务数据管理方法
CN116932919A (zh) * 2023-09-15 2023-10-24 中关村科学城城市大脑股份有限公司 信息推送方法、装置、电子设备和计算机可读介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116308682B (zh) * 2023-05-12 2023-10-27 阿里巴巴（中国）有限公司 提供商品信息的方法及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150108213A1 (en) * 2013-10-23 2015-04-23 Toshiba Tec Kabushiki Kaisha Shopping support device and shopping support method
CN108335177A (zh) * 2018-03-09 2018-07-27 京东方科技集团股份有限公司 购物推荐方法、用户端、服务端、设备和存储介质
CN108346073A (zh) * 2017-01-23 2018-07-31 北京京东尚科信息技术有限公司 一种语音购物方法和装置
CN109102320A (zh) * 2018-07-02 2018-12-28 大连大商天狗电子商务有限公司 一种智能引导系统
JP2019049848A (ja) * 2017-09-08 2019-03-28 卓真 泉 取引支援システム、取引支援方法及びプログラム

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102323928A (zh) * 2011-08-22 2012-01-18 苏州阔地网络科技有限公司 一种组件自动推荐方法及装置
CN105528374A (zh) * 2014-10-21 2016-04-27 苏宁云商集团股份有限公司 一种电子商务中的商品推荐方法及其系统
CN107316645B (zh) * 2017-06-01 2021-10-12 北京京东尚科信息技术有限公司 一种语音购物的方法和系统
CN107993133A (zh) * 2018-01-23 2018-05-04 北京知行信科技有限公司 一种基于自然语言的智能分析推荐方法及系统
CN108520058B (zh) * 2018-03-30 2021-09-24 维沃移动通信有限公司 一种商家信息推荐方法及移动终端
CN109697629B (zh) * 2018-11-15 2023-02-24 平安科技（深圳）有限公司 产品数据推送方法及装置、存储介质、计算机设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150108213A1 (en) * 2013-10-23 2015-04-23 Toshiba Tec Kabushiki Kaisha Shopping support device and shopping support method
CN108346073A (zh) * 2017-01-23 2018-07-31 北京京东尚科信息技术有限公司 一种语音购物方法和装置
JP2019049848A (ja) * 2017-09-08 2019-03-28 卓真 泉 取引支援システム、取引支援方法及びプログラム
CN108335177A (zh) * 2018-03-09 2018-07-27 京东方科技集团股份有限公司 购物推荐方法、用户端、服务端、设备和存储介质
CN109102320A (zh) * 2018-07-02 2018-12-28 大连大商天狗电子商务有限公司 一种智能引导系统

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112492518A (zh) * 2020-12-09 2021-03-12 深圳市欢太科技有限公司 卡片确定方法、装置、电子设备及存储介质
CN112492518B (zh) * 2020-12-09 2023-08-15 深圳市欢太数字科技有限公司 卡片确定方法、装置、电子设备及存储介质
CN112905148A (zh) * 2021-03-12 2021-06-04 拉扎斯网络科技（上海）有限公司 一种语音播报的控制方法和装置，存储介质和电子设备
CN112905148B (zh) * 2021-03-12 2023-09-22 拉扎斯网络科技（上海）有限公司 一种语音播报的控制方法和装置，存储介质和电子设备
CN113158056A (zh) * 2021-04-27 2021-07-23 口碑(上海)信息技术有限公司 推荐语的生成方法及装置
CN113239268B (zh) * 2021-04-29 2023-04-07 佛山科学技术学院 一种商品推荐方法、装置及系统
CN113239268A (zh) * 2021-04-29 2021-08-10 佛山科学技术学院 一种商品推荐方法、装置及系统
CN113327134A (zh) * 2021-06-16 2021-08-31 北京百度网讯科技有限公司 商品信息推荐方法及装置、电子设备和介质
CN113327134B (zh) * 2021-06-16 2024-01-16 北京百度网讯科技有限公司 商品信息推荐方法及装置、电子设备和介质
CN113592530B (zh) * 2021-06-24 2023-08-22 青岛海尔科技有限公司 用于业务提供方的推荐方法、装置及电子设备
CN113592530A (zh) * 2021-06-24 2021-11-02 青岛海尔科技有限公司 用于业务提供方的推荐方法、装置及电子设备
CN113506152A (zh) * 2021-07-08 2021-10-15 四川新龟科技有限公司 一种商品下单方法、装置、设备及存储介质
CN113902466A (zh) * 2021-09-09 2022-01-07 广景视睿科技（深圳）有限公司 一种无人商店交互方法、无人商店及存储介质
CN114327349A (zh) * 2021-12-13 2022-04-12 青岛海尔科技有限公司 智能卡片的确定方法及装置、存储介质、电子装置
CN114327349B (zh) * 2021-12-13 2024-03-22 青岛海尔科技有限公司 智能卡片的确定方法及装置、存储介质、电子装置
CN116452303A (zh) * 2023-06-14 2023-07-18 深圳市诚识科技有限公司 基于大数据的电子商务数据管理方法
CN116452303B (zh) * 2023-06-14 2023-10-03 深圳市诚识科技有限公司 基于大数据的电子商务数据管理方法
CN116932919A (zh) * 2023-09-15 2023-10-24 中关村科学城城市大脑股份有限公司 信息推送方法、装置、电子设备和计算机可读介质
CN116932919B (zh) * 2023-09-15 2023-11-24 中关村科学城城市大脑股份有限公司 信息推送方法、装置、电子设备和计算机可读介质

Also Published As

Publication number Publication date
CN113366524B (zh) 2024-05-10
CN113366524A (zh) 2021-09-07

Similar Documents

Publication Publication Date Title
WO2020232615A1 (zh) 信息推荐方法、装置、电子设备以及存储介质
US9930167B2 (en) Messaging application with in-application search functionality
WO2018086462A1 (zh) 一种业务数据的加载、推送、交互信息的生成方法和装置
US10845949B2 (en) Continuity of experience card for index
US20120221411A1 (en) Apparatus and methods for determining user intent and providing targeted content according to intent
KR20140087043A (ko) 웹페이지들로부터의 어플리케이션 런칭
KR102219275B1 (ko) 설치-후 어플리케이션 인터렉션 개선하기
CN108763579A (zh) 搜索内容推荐方法、装置、终端设备及存储介质
KR20130028916A (ko) 다른 사용자의 사용자 선호에 기초하여 사용자에 대하여 디스플레이되는 컨텐츠 커스터마이징
WO2019205804A1 (zh) 网页预下载方法及装置、存储介质和电子装置
CN111899068A (zh) 商品导购方法、装置、存储介质及计算机设备
CN105095253A (zh) 网页显示方法及装置
WO2020232616A1 (zh) 信息推荐方法、装置、电子设备以及存储介质
CN105893624A (zh) 一种数据显示方法以及系统
CN111444448B (zh) 一种数据处理方法、服务器及系统
WO2021087684A1 (zh) 用户行为数据处理方法、装置、服务器及存储介质
WO2020232617A1 (zh) 语音信息处理方法、装置、电子设备以及存储介质
CN113330475B (zh) 信息推荐方法、装置、电子设备以及存储介质
WO2022199494A1 (zh) 一种基于用户兴趣的内容推荐方法与终端设备
CN107291953A (zh) 一种信息查询方法、装置、电子设备及存储介质
CN108897774B (zh) 一种获取新闻热点的方法、设备及存储介质
WO2020258082A1 (zh) 信息推荐方法、装置、电子设备以及存储介质
CN117252730B (zh) 服务订阅处理系统、服务订阅信息处理方法与装置
US11663632B2 (en) Network server and method for providing web pages to user terminals
CN112925982B (zh) 用户重定向方法及装置、存储介质、计算机设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19930062

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 22.04.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19930062

Country of ref document: EP

Kind code of ref document: A1