Information recommendation method, device and electronic device

Abstract

The embodiments of the present invention provide an information recommendation method, device and electronic device, wherein the method comprises: obtaining conversation scenario information; performing user emotion analysis based on the conversation scenario information to determine corresponding emotion information; searching for conversation information matching the emotion information and displaying the conversation information; and then making recommendations based on the user's emotion information, so that the recommended information can better meet the user's needs, and the user can directly select the conversation information for reply without having to manually input word by word or bothering with the information to be input, thereby improving input efficiency.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an information recommendation method, device and electronic equipment. Background Art

[0002] With the development of computer technology, electronic devices such as mobile phones and tablet computers are becoming more and more popular, bringing great convenience to people's life, study and work. These electronic devices are usually installed with input method applications (input methods for short), so that users can use the input methods to input information.

[0003] When users interact through instant messaging, they can usually use input methods to input information to achieve interaction. During the interaction process, the input method will recommend corresponding reply information for the message sent by the other party, which is convenient for the user to reply; for example, the other party sends a message "I don't want to talk anymore", and the input method recommends the message "Okay". However, the existing input methods are not smart enough to recommend reply messages, which is not conducive to the continuous advancement of the conversation; for example, based on the above example, when the other party chooses the recommended message "Okay" to reply, the chat conversation is likely to terminate; if the user wants to continue the chat conversation, he needs to manually enter the sentence he wants to reply, such as "Don't be angry", which is cumbersome and has low input efficiency. Summary of the invention

[0004] An embodiment of the present invention provides an information recommendation method to improve input efficiency.

[0005] Correspondingly, the embodiment of the present invention further provides an information recommendation device and an electronic device to ensure the implementation and application of the above method.

[0006] In order to solve the above problems, an embodiment of the present invention discloses an information recommendation method, which specifically includes: obtaining conversation scenario information; performing user sentiment analysis based on the conversation scenario information to determine corresponding sentiment information; searching for conversation information that matches the sentiment information and displaying the conversation information.

[0007] Optionally, performing user sentiment analysis based on the conversation scenario information to determine corresponding sentiment information includes: determining keywords corresponding to the conversation scenario information; determining sentiment values ​​corresponding to each keyword, and determining the sentiment information based on the sentiment values ​​corresponding to each keyword.

[0008] Optionally, searching for session information matching the emotion information includes: searching for mapping information based on the emotion information to determine matching session information.

[0009] Optionally, the session information includes multiple items, and the method further includes the step of filtering the session information: filtering the session information based on the session scenario information; and / or filtering the session information based on the historical click frequency corresponding to the session information; and / or filtering the session information based on historical feedback information for the session information.

[0010] Optionally, the session information includes statements of multiple terminals, and the terminals include the local terminal and other terminals; and displaying the session information includes: displaying the statement of the local terminal in the session information.

[0011] Optionally, the local end includes multiple statements, and the method further includes: receiving a screen-up instruction; displaying the first local end statement in the session information corresponding to the screen-up instruction; receiving the other end information; if the other end information matches the statements of other ends in the session information, then displaying the next local end statement of the session information on the screen.

[0012] Optionally, the emotion information includes: emotion information of the user at the local end and / or emotion information of the user at the opposite end.

[0013] An embodiment of the present invention also discloses an information recommendation device, which specifically includes: an information acquisition module, used to acquire conversation scene information; an emotion determination module, used to perform user emotion analysis based on the conversation scene information and determine corresponding emotion information; an information determination module, used to search for conversation information matching the emotion information and display the conversation information.

[0014] Optionally, the emotion determination module is used to determine the keywords corresponding to the conversation scenario information; determine the emotion value corresponding to each keyword, and determine the emotion information according to the emotion value corresponding to each keyword.

[0015] Optionally, the information determination module includes: a session information determination submodule, which is used to search for mapping information based on the emotion information to determine matching session information.

[0016] Optionally, the session information includes multiple items, and the device also includes a filtering module: the filtering module is used to filter the session information based on the session scenario information; and / or, to filter the session information based on the historical click frequency corresponding to the session information; and / or, to filter the session information based on historical feedback information for the session information.

[0017] Optionally, the session information includes statements of multiple terminals, the terminals including the local terminal and other terminals; the information determination module includes: a session information display submodule, used to display the statements of the local terminal in the session information.

[0018] Optionally, the local end includes multiple statements, and the device also includes: an instruction receiving module for receiving a screen-up instruction; a screen-up module for displaying the first local end statement in the session information corresponding to the screen-up instruction; and a matching module for displaying the next local end statement of the session information if the peer end information matches the statements of other ends in the session information.

[0019] Optionally, the emotion information includes: emotion information of the user at the local end and / or emotion information of the user at the opposite end.

[0020] An embodiment of the present invention further discloses a readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the information recommendation method as described in any one of the embodiments of the present invention.

[0021] An embodiment of the present invention also discloses an electronic device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: obtaining conversation scenario information; performing user emotion analysis based on the conversation scenario information to determine corresponding emotion information; searching for conversation information that matches the emotion information and displaying the conversation information.

[0022] Optionally, performing user sentiment analysis based on the conversation scenario information to determine corresponding sentiment information includes: determining keywords corresponding to the conversation scenario information; determining sentiment values ​​corresponding to each keyword, and determining the sentiment information based on the sentiment values ​​corresponding to each keyword.

[0023] Optionally, searching for session information matching the emotion information includes: searching for mapping information based on the emotion information to determine matching session information.

[0024] Optionally, the session information includes multiple items, and the electronic device also includes a step of filtering the session information: filtering the session information based on the session scenario information; and / or filtering the session information based on a historical click frequency corresponding to the session information; and / or filtering the session information based on historical feedback information for the session information.

[0025] Optionally, the session information includes statements of multiple terminals, and the terminals include the local terminal and other terminals; and displaying the session information includes: displaying the statement of the local terminal in the session information.

[0026] Optionally, the local end statement includes multiple statements and also includes instructions for performing the following operations: receiving an on-screen instruction; displaying the on-screen instruction corresponding to the first local end statement in the session information; receiving the other end information; if the other end information matches the statements of other ends in the session information, then displaying the next local end statement of the session information on the screen.

[0027] Optionally, the emotion information includes: emotion information of the user at the local end and / or emotion information of the user at the opposite end.

[0028] The embodiments of the present invention include the following advantages:

[0029] In an embodiment of the present invention, conversation scenario information can be obtained, and then user emotion analysis can be performed based on the conversation scenario information to determine corresponding emotion information; then conversation information matching the emotion information can be searched and displayed; and then recommendations can be made based on the user's emotion information, so that the recommended information can better meet the user's needs. The user can directly select the conversation information to reply without having to manually enter it word by word or bothering to figure out the information that needs to be entered, thereby improving input efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flowchart of steps of an information recommendation method embodiment of the present invention;

[0031] Figure 2 is a flowchart of steps of an optional embodiment of an information recommendation method of the present invention;

[0032] Figure 3 is a structural block diagram of an embodiment of an information recommendation device of the present invention;

[0033] Figure 4 is a structural block diagram of an optional embodiment of an information recommendation device of the present invention;

[0034] Figure 5 A structural block diagram of an electronic device for information recommendation according to an exemplary embodiment;

[0035] Figure 6 It is a structural schematic diagram of an electronic device for information recommendation according to another exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0037] One of the core concepts of the embodiments of the present invention is to recommend conversation information that meets the sentiment analysis results to users by performing user sentiment analysis, so that the recommended conversation information can better meet user needs, and users do not need to manually and painstakingly think about the information that needs to be input, thereby improving input efficiency.

[0038] Reference Figure 1 , shows a flowchart of an information recommendation method embodiment of the present invention, which may specifically include the following steps:

[0039] Step 102: Obtain session scenario information.

[0040] In the embodiment of the present invention, the user can enter the communication interface corresponding to the communication application according to his own needs and communicate with other users. The communication application can be an instant messaging application such as a social software, or a short message application. Therefore, when the user enters the communication interface of the communication application in the terminal device and talks with other users, after receiving the information from the other end, the conversation scenario information can be obtained, and then the corresponding reply information can be recommended to the user based on the conversation scenario information; wherein, the conversation scenario information can include a variety of information, such as the above information, and the related information of the above information such as environment, time, etc., which is not limited in the embodiment of the present invention.

[0041] Step 104: Perform user sentiment analysis based on the conversation scenario information to determine corresponding sentiment information.

[0042] In an embodiment of the present invention, in order to make the information recommended to the user more able to meet the user's needs, user emotion analysis can be performed based on the conversation scene information, for example, by using emotion recognition technology in the field of artificial intelligence, user emotion analysis is implemented by analyzing the emotions of each keyword in the conversation scene information, and the corresponding emotion information is determined; wherein, the emotion information may include the emotion information of the user at the local end, and may also include the emotion information of the user at the opposite end. For example, the information at the opposite end in the conversation scene information: "I feel so sad today, I want to cry"; the user emotion analysis can be performed based on the conversation scene information, and it can be determined that the emotion information of the user at the opposite end is "sad". For another example, the information at the local end in the conversation scene information: "I found that you are a photo fraud, because you are much more beautiful in person than in the photo", the information at the opposite end: "No, thank you for the compliment"; the user emotion analysis can be performed based on the conversation scene information, and it can be determined that the emotion information of the user at the local end is "want to pick up girls".

[0043] Step 106: Search for session information that matches the emotion information and display the session information.

[0044] In the embodiment of the present invention, multiple segments of conversation information can be collected in advance, and then for each segment of conversation information, the emotional information matching the segment of conversation information can be determined; for example, the emotional information matching a segment of consolation-type conversation information can be "sad", the emotional information matching a segment of appeasement-type conversation information can be "angry", the emotional information matching a segment of earthy love talk-type conversation information can be "want to flirt with a girl", etc. After determining the emotional information corresponding to the user, the conversation information matching the emotional information can be searched, and then the conversation information can be displayed; wherein, the area for displaying the conversation information can be set according to demand, such as the display area of ​​the input method such as the candidate area, the association area, etc., or the display area of ​​the communication application, which is not limited by the present invention.

[0045] As an example of the present invention, user A enters chat application X to chat with user B. After user A sends a message "Why do you talk so little today?", user B replies "It's okay, I've always talked very little"; at this time, the input method of the corresponding terminal device of user A can obtain the conversation scene information such as the above information, including: the local information "Why do you talk so little today?", the opposite end information "It's okay, I've always talked very little"; then perform user emotion analysis based on the conversation scene information to determine the corresponding emotion information, for example, determine the opposite end user's emotion information as "angry" based on the above conversation scene information; then search for the conversation information that matches the emotion information, for example, the conversation information that matches the emotion information "angry" such as "Okay, don't be angry, I'll buy you something delicious", and then display the conversation information. After user A subsequently selects "Okay, don't be angry, I'll buy you something delicious" from the displayed conversation information to reply, user B may reply to this question, such as "Okay, I want to eat ******", and user A can continue to reply; thus, the conversation can continue and help users to appease the other party's emotions.

[0046] As an example of the present invention, user C enters the chat application M to chat with user D. After user C sends the message "You gave a great speech today, and it's nice to meet you", user C receives a reply message from user D "Thank you, and I'm glad to meet you too"; at this time, the input method of the corresponding terminal device of user C can obtain session scene information such as the above information, including: local information: "You gave a great speech today, and it's nice to meet you", and the other end information: "Thank you, and I'm glad to meet you too"; then user emotion analysis is performed based on the session scene information to determine the corresponding emotion information, for example, based on the above session scene information, it is determined that the emotion information of the local user is "want to pick up girls"; then the session information that matches the emotion information is searched, for example, session information that matches the emotion information "want to pick up girls" with earthy love words such as "Today either you die or I die, you are so cute, I love you to death", and then the session information is displayed. After user C selects the conversation message "Today either you die or I die, you are so cute, I love you so much" and replies, user D will reply to this question, such as "Hahaha, you are so good at talking", and user C can continue to reply, which can keep the conversation going and help users to pick up girls better.

[0047] In an embodiment of the present invention, conversation scenario information can be obtained, and then user emotion analysis can be performed based on the conversation scenario information to determine corresponding emotion information; then conversation information matching the emotion information can be searched and displayed; and then recommendations can be made based on the user's emotion information, so that the recommended information can better meet the user's needs. The user can directly select the conversation information to reply without having to manually enter it word by word or bothering to figure out the information that needs to be entered, thereby improving input efficiency.

[0048] Reference Figure 2 , shows a flowchart of an optional embodiment of an information recommendation method of the present invention, which may specifically include the following steps:

[0049] Step 202: Obtain session scenario information.

[0050] In the embodiment of the present invention, users can use instant messaging applications and short message applications to exchange information. When the input method is in the communication interface of a communication application and receives a message from the other end, it can obtain the conversation scene information in the communication interface. The conversation scene information may include: the above information and the associated information of the above information.

[0051] Wherein, the above information may include local information and peer information; wherein, there are multiple ways to obtain the above information. In one example of the present invention, one way to obtain the above information may be to obtain the chat record corresponding to the communication interface, and then select the above information from the chat record. In an embodiment of the present invention, the input method may send a request to obtain the chat record to the corresponding communication application, and the request may include a set time, and the set time may be set as required, such as 1 hour, 1 day; after the communication application receives the request to obtain the chat record, it may determine and extract the chat record within the set time according to the current time and the set time, as well as the timestamp of each chat record, and then return the extracted chat record to the input method; and then the input method may use the received chat record as the above information. In one example of the present invention, another way to obtain the above information may be to take a screenshot of the current communication interface, and then perform OCR (Optical Character Recognition) analysis on the image obtained by the screenshot, and use the text obtained by the OCR analysis as the above information, which is not limited in the embodiment of the present invention.

[0052] The associated information may include information related to the above information, and may include at least one of the following: environmental information, location information, weather information, and time information; of course, other information may also be included, which is not limited in the embodiment of the present invention.

[0053] Step 204: Determine keywords corresponding to the conversation scenario information.

[0054] Step 206: Determine the sentiment value corresponding to each keyword, and determine the sentiment information according to the sentiment value corresponding to each keyword.

[0055] In an embodiment of the present invention, multiple segments of historical conversation scene information and corresponding reference emotion information may be acquired in advance. The historical conversation scene information may include historical conversation scene information corresponding to the user, or may include historical conversation scene information corresponding to users of the entire network. The embodiment of the present invention does not impose any restrictions on this.

[0056] In an embodiment of the present invention, for each historical conversation scene information, the historical conversation scene information can be analyzed to determine the corresponding keywords; then, the sentiment value corresponding to each keyword can be determined by searching the sentiment dictionary; wherein, the sentiment dictionary can include a self-edited dictionary and an existing dictionary, each word in the sentiment dictionary has a corresponding sentiment value, and the sentiment value can be a multidimensional vector, each dimension corresponds to a sentiment, and the value of each dimension can refer to the score of the sentiment corresponding to the dimension. wherein, the self-edited dictionary can refer to a dictionary with manually annotated sentiment values, and the existing dictionary can include an existing sentiment dictionary such as a HowNet sentiment dictionary, a Chinese sentiment polarity dictionary, etc. then, the historical conversation scene information, the sentiment values ​​corresponding to the keywords in the historical conversation scene information, and the corresponding reference sentiment information are used to train the machine learning model; for example, the keywords and the corresponding sentiment values ​​in the historical conversation scene information can be input into the machine learning model to obtain the sentiment information output by the machine learning model, and then the sentiment information output by the machine learning model is compared with the reference sentiment information corresponding to the historical conversation scene information, and the machine learning model is reversely trained. and then, the trained machine learning model can be used to perform user sentiment analysis and determine the sentiment information.

[0057] In an embodiment of the present invention, the historical conversation scene information may include text or pictures, and the present invention does not limit this; if the historical conversation scene information is text, then for each segment of text, natural language processing may be performed on the segment, such as word segmentation processing on the segment to obtain word segmentation fragments, and then the keywords corresponding to the segment are determined based on each word segmentation fragment. If the historical conversation scene information is a picture, for each picture, the subject words of the picture may be obtained as the corresponding keywords; or the picture may be subjected to OCR analysis to obtain the corresponding recognition text and determine the keywords corresponding to the recognition text, and then the keywords of the recognition text may be used as the keywords of the picture.

[0058] Therefore, after obtaining the conversation scene information, if the conversation scene information is text, natural language processing can be performed on the conversation scene information, such as word segmentation processing to obtain corresponding word segmentation fragments, and then the keywords corresponding to the conversation scene information are determined based on the word segmentation fragments. If the conversation scene is a picture, the subject words of the conversation scene information are obtained, and the subject words are used as the key to the conversation scene information; or the conversation scene information is subjected to OCR analysis to determine the keywords corresponding to the conversation scene information. Then the sentiment value corresponding to each keyword is determined; wherein, the method of determining the sentiment value corresponding to each keyword in the conversation scene information is similar to the above-mentioned method of determining the sentiment value of each keyword in the historical conversation scene information, and will not be repeated here. Then, each keyword and the corresponding sentiment value in the conversation scene information can be input into the trained machine learning model, and the sentiment information of the local user and / or the opposite user can be obtained.

[0059] Step 208: Search for mapping information based on the emotion information to determine matching session information.

[0060] In the embodiment of the present invention, multiple segments of session information can be collected in advance, and after determining the emotion information matching each segment of session information, mapping information between each segment of session information and the corresponding matching emotion information can be established respectively, and then the session information and the corresponding mapping information can be stored in a database. After determining the emotion information corresponding to the user, the mapping information can be searched from the database based on the emotion information to determine the session information matching the emotion information.

[0061] Step 210: Filter session information.

[0062] In the embodiment of the present invention, the conversation information matching the emotion information may include multiple ones, so the matched conversation information may be screened so that the recommended information can better meet the user's needs and further improve the input efficiency.

[0063] Some session information may be related to the session scenario information, while some may be unrelated to the session scenario information; therefore, in one example of the present invention, a method of filtering session information may be to filter the session information based on the session scenario information. Among them, the correlation between each session information and the session scenario information may be calculated, and the session information with high correlation to the session scenario information may be selected, and the session information with low correlation to the session scenario information may be filtered out. Of course, in an optional embodiment of the present invention, while pre-acquiring the session information, the historical session information corresponding to each session information may be acquired, and then the mapping information between the historical session scenario information, the session information and the corresponding matching emotional information may be established; and then, the mapping relationship may be searched based on the session scenario information and the emotional information to determine the corresponding session information; this is not limited in the embodiment of the present invention.

[0064] In an embodiment of the present invention, the session information can be filtered according to the user's preference for the session information, wherein the user is likely to frequently click on the preferred session information, while the user is likely to have a relatively low frequency of clicking on the disliked session information; therefore, the historical click frequency corresponding to the session information can be used to characterize the user's preference for the session information, and the historical click frequency can be proportional to the preference. In an example of the present invention, another way to filter the session information can be to filter the session information according to the historical click frequency corresponding to the session information. Among them, the historical click frequency corresponding to each session information can be counted, and then the session information with a high historical click frequency is selected, and the session information with a low historical click frequency is filtered.

[0065] In addition, the feedback information of users for different preferences of session information may also be different. For example, based on the above example: User C: "You gave a great speech today, it's nice to meet you", User D: "Thank you, I'm also happy to meet you", if the session information replied by user C is: "It's either you or me today, you are so cute, I love you so much", the reply of user D may be: "It's so boring"; if the session information replied by user C is: "I wonder if I can ask you about the next speech?", the reply of user D may be: "Okay, no problem". Therefore, in an embodiment of the present invention, the user's preference for the session information can be determined based on the feedback information for the session information. In an example of the present invention, the session information can be filtered based on the historical feedback information for the session information; wherein, the user's historical feedback information for each session information can be determined, and then the user's preference for each session information can be determined based on the historical feedback information, and then the session information can be filtered based on the user's preference for each session information. Among them, session information with low preference can be filtered out; the historical feedback information for the session information can refer to the historical feedback information of the opposite user corresponding to the local user, and can also include the historical feedback information of all users for the session information, which is not limited in the embodiment of the present invention.

[0066] Step 212: Display the filtered session information.

[0067] In the embodiment of the present invention, when the filtered session information includes multiple sessions, if the session information is filtered according to the relevance to the session scenario information, it can be displayed from high to low according to the relevance corresponding to the session information; if the session information is filtered according to the user's preference, it can be displayed from high to low according to the preference corresponding to the session information; of course, the relevance and preference corresponding to the session information can also be weighted, and the session information can be displayed from high to low according to the weighted result, and the embodiment of the present invention does not limit this. Among them, one session information includes statements of multiple terminals, and the terminals include the local terminal and other terminals, and the other terminals can include other terminals other than the local terminal; for example, "Let's exchange gifts, okay? (this terminal), yes, yes! (the other terminal), okay, from now on you are mine, and I am yours (this terminal)". Of course, each session information can also only include the statements of the local terminal, such as "Don't be sad, we will have a big meal on the weekend (this terminal)"; the embodiment of the present invention does not limit this. If the session information includes statements of multiple terminals, then when the filtered session information is displayed locally, for each session information, only the statements of the local end in the session information may be displayed; for example, in the above example, the session information: "Shall we exchange gifts? (this end) Sure, sure!, (the other end) Okay, from now on you are mine and I am yours (this end)", then only "Shall we exchange gifts? Sure, from now on you are mine and I am yours" may be displayed for the user to choose.

[0068] In an optional embodiment of the present invention, for each session information, the local statements in the session information may include multiple statements. After displaying the filtered session information, the user can perform the screen operation. Correspondingly, the input method can receive the screen instruction; the screen instruction corresponds to the first local statement in the session information, and then waits for the opposite user to reply. After the opposite user replies, the opposite information can be received. If the opposite information matches the statements of other ends in the session information, the next local statement of the session information can be screened; wherein, the opposite information received this time can be matched with the other end statements after the user's most recent screened local statement and before the next local statement in the session information. If the two match, the next local statement after the most recent screen statement can be screened. This can be followed by analogy, and subsequent local statements in the session information can be screened one by one.

[0069] In summary, in the embodiments of the present invention, conversation scenario information can be obtained, and then user sentiment analysis can be performed based on the conversation scenario information to determine corresponding sentiment information; then conversation information matching the sentiment information can be searched for and the conversation information can be displayed; and then recommendations can be made based on the user's sentiment information, so that the recommended information can better meet the user's needs, and the user can directly select the conversation information to reply without having to manually enter it word by word or bothering with the information that needs to be entered, thereby improving input efficiency.

[0070] Secondly, in an embodiment of the present invention, it is possible to determine the keywords corresponding to the conversation scene information, and then determine the sentiment value corresponding to each keyword, and determine the sentiment information based on the sentiment value corresponding to each keyword; thereby accurately performing user sentiment analysis, improving the accuracy of determining conversation information, and further improving information input efficiency.

[0071] Furthermore, in an embodiment of the present invention, the session information may include multiple items. After determining the session information matching the emotion information, the session information may be screened; wherein the session information may be screened based on the session scene information; and / or the session information may be screened based on the historical click frequency corresponding to the session information; and / or the session information may be screened based on the feedback information for the session information. Thus, the session information that better meets the user's needs may be screened out, further improving the efficiency of information input.

[0072] Again, in an embodiment of the present invention, the session information may include statements of multiple terminals, including the local terminal and other terminals; and then the statements of the local terminal in the session information may be displayed. In one session information, the local terminal may include multiple statements, and then a screen instruction may be received; the screen instruction corresponds to the first local terminal statement in the session information; after the other terminal replies, the other terminal information may be received; if the other terminal information matches the statements of other terminals in the session information, the next local terminal statement of the session information may be displayed; and then the user does not need to select again, thereby improving input efficiency.

[0073] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0074] Reference Figure 3 , shows a structural block diagram of an information recommendation device embodiment of the present invention, which may specifically include the following modules:

[0075] Information acquisition module 302, used to acquire session scenario information;

[0076] The emotion determination module 304 is used to perform user emotion analysis based on the conversation scenario information and determine corresponding emotion information;

[0077] The information determination module 306 is used to search for the session information matching the emotion information and display the session information.

[0078] Reference Figure 4 , shows a structural block diagram of an optional embodiment of an information recommendation device of the present invention.

[0079] In an optional embodiment of the present invention, the emotion determination module 304 is used to determine the keywords corresponding to the conversation scenario information; determine the emotion value corresponding to each keyword, and determine the emotion information according to the emotion value corresponding to each keyword.

[0080] In an optional embodiment of the present invention, the information determination module 306 includes:

[0081] The session information determination submodule 3062 is used to search for mapping information based on the emotion information to determine matching session information.

[0082] In an optional embodiment of the present invention, the session information includes multiple items, and the device further includes a screening module 308:

[0083] The filtering module 308 is used to filter the session information according to the session scenario information; and / or, filter the session information according to the historical click frequency corresponding to the session information; and / or, filter the session information according to the historical feedback information for the session information.

[0084] In an optional embodiment of the present invention, the session information includes statements of multiple terminals, and the terminals include the local terminal and other terminals; the information determination module 306 includes:

[0085] The session information display submodule 3064 is used to display the statements of the local end in the session information.

[0086] In an optional embodiment of the present invention, the local end includes a plurality of statements, and the device further includes:

[0087] The instruction receiving module 310 is used to receive the screen display instruction;

[0088] The screen display module 312 is used to display the first local end sentence in the conversation information corresponding to the screen display instruction;

[0089] The matching module 314 is configured to display the next local end statement of the session information on the screen if the peer end information matches the statement of the other end in the session information.

[0090] In an optional embodiment of the present invention, the emotional information includes: emotional information of the user at the local end and / or emotional information of the user at the opposite end.

[0091] In summary, in the embodiments of the present invention, conversation scenario information can be obtained, and then user sentiment analysis can be performed based on the conversation scenario information to determine corresponding sentiment information; then conversation information matching the sentiment information can be searched for and the conversation information can be displayed; and then recommendations can be made based on the user's sentiment information, so that the recommended information can better meet the user's needs, and the user can directly select the conversation information to reply without having to manually enter it word by word or bothering with the information that needs to be entered, thereby improving input efficiency.

[0092] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0093] Figure 5 1 is a block diagram of an electronic device 500 for information recommendation according to an exemplary embodiment. For example, the electronic device 500 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0094] Reference Figure 5 , the electronic device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0095] The processing component 502 generally controls the overall operation of the electronic device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 508 and the processing component 502.

[0096] The memory 504 is configured to store various types of data to support operations on the device 500. Examples of such data include instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, videos, etc. The memory 504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0097] The power component 506 provides power to the various components of the electronic device 500. The power component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 500.

[0098] The multimedia component 508 includes a screen that provides an output interface between the electronic device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front camera and / or a rear camera. When the electronic device 500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0099] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), and when the electronic device 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 504 or sent via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0100] I / O interface 512 provides an interface between processing component 502 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0101] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the electronic device 500. For example, the sensor assembly 514 can detect the open / closed state of the device 500, the relative positioning of components, such as the display and keypad of the electronic device 500, and the sensor assembly 514 can also detect the position change of the electronic device 500 or a component of the electronic device 500, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and the temperature change of the electronic device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0102] The communication component 516 is configured to facilitate wired or wireless communication between the electronic device 500 and other devices. The electronic device 500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 514 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 514 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0103] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0104] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the instructions can be executed by a processor 520 of an electronic device 500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0105] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute an information recommendation method, the method comprising: obtaining conversation scene information; performing user emotion analysis based on the conversation scene information to determine corresponding emotion information; searching for conversation information that matches the emotion information and displaying the conversation information.

[0106] Optionally, performing user sentiment analysis based on the conversation scenario information to determine corresponding sentiment information includes: determining keywords corresponding to the conversation scenario information; determining sentiment values ​​corresponding to each keyword, and determining the sentiment information based on the sentiment values ​​corresponding to each keyword.

[0107] Optionally, searching for session information matching the emotion information includes: searching for mapping information based on the emotion information to determine matching session information.

[0108] Optionally, the session information includes multiple items, and the method further includes the step of filtering the session information: filtering the session information based on the session scenario information; and / or filtering the session information based on the historical click frequency corresponding to the session information; and / or filtering the session information based on historical feedback information for the session information.

[0109] Optionally, the session information includes statements of multiple terminals, and the terminals include the local terminal and other terminals; and displaying the session information includes: displaying the statement of the local terminal in the session information.

[0110] Optionally, the local end includes multiple statements, and the method further includes: receiving a screen-up instruction; displaying the first local end statement in the session information corresponding to the screen-up instruction; receiving the other end information; if the other end information matches the statements of other ends in the session information, then displaying the next local end statement of the session information on the screen.

[0111] Optionally, the emotion information includes: emotion information of the user at the local end and / or emotion information of the user at the opposite end.

[0112] Figure 6: is a structural diagram of an electronic device 600 for information recommendation according to another exemplary embodiment of the present invention. The electronic device 600 may be a server, which may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 622 (for example, one or more processors) and a memory 632, and one or more storage media 630 (for example, one or more mass storage devices) storing application programs 642 or data 644. Among them, the memory 632 and the storage medium 630 may be temporary storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processor 622 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the server.

[0113] The server may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input and output interfaces 658, one or more keyboards 656, and / or one or more operating systems 641, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0114] An electronic device includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: obtaining conversation scene information; performing user emotion analysis based on the conversation scene information to determine corresponding emotion information; searching for conversation information that matches the emotion information and displaying the conversation information.

[0115] Optionally, performing user sentiment analysis based on the conversation scenario information to determine corresponding sentiment information includes: determining keywords corresponding to the conversation scenario information; determining sentiment values ​​corresponding to each keyword, and determining the sentiment information based on the sentiment values ​​corresponding to each keyword.

[0116] Optionally, searching for session information matching the emotion information includes: searching for mapping information based on the emotion information to determine matching session information.

[0117] Optionally, the session information includes multiple items, and the electronic device also includes a step of filtering the session information: filtering the session information based on the session scenario information; and / or filtering the session information based on a historical click frequency corresponding to the session information; and / or filtering the session information based on historical feedback information for the session information.

[0118] Optionally, the session information includes statements of multiple terminals, and the terminals include the local terminal and other terminals; and displaying the session information includes: displaying the statement of the local terminal in the session information.

[0119] Optionally, the local end statement includes multiple statements and also includes instructions for performing the following operations: receiving an on-screen instruction; displaying the on-screen instruction corresponding to the first local end statement in the session information; receiving the other end information; if the other end information matches the statements of other ends in the session information, then displaying the next local end statement of the session information on the screen.

[0120] Optionally, the emotion information includes: emotion information of the user at the local end and / or emotion information of the user at the opposite end.

[0121] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0122] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0125] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0126] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0127] The above is a detailed introduction to an information recommendation method, an information recommendation device and an electronic device provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An information recommendation method, characterized in that: include: Get session scenario information; Performing user sentiment analysis based on the conversation scenario information to determine corresponding sentiment information; The emotional information includes: the emotional information of the user at the local end and the emotional information of the user at the other end; Searching for session information matching the emotion information, and displaying the session information; The session information is filtered according to historical feedback information of the opposite end user corresponding to the local end user with respect to the session information.

2. The method according to claim 1, characterized in that: The performing user emotion analysis based on the conversation scenario information to determine corresponding emotion information includes: Determining keywords corresponding to the conversation scenario information; Determine the sentiment value corresponding to each keyword, and determine the sentiment information according to the sentiment value corresponding to each keyword.

3. The method according to claim 1, characterized in that The searching for the session information matching the emotion information includes: Mapping information is searched based on the emotion information to determine matching session information.

4. The method according to claim 1, characterized in that: The session information includes statements of multiple terminals, and the terminals include the local terminal and other terminals; The presenting of the session information includes: Display the statements of the local end in the session information.

5. The method according to claim 4, characterized in that The local end includes a plurality of statements, and the method further includes: Receive screen display instructions; The upper screen instruction corresponds to the first local end statement in the session information; Receive information from the other end; If the peer end information matches the statements of the other end in the session information, the next local end statement of the session information is displayed on the screen.

6. An information recommendation device, characterized in that: include: An information acquisition module, used to acquire session scenario information; An emotion determination module, used to perform user emotion analysis based on the conversation scenario information and determine corresponding emotion information; The emotional information includes: the emotional information of the user at the local end and the emotional information of the user at the other end; An information determination module, used to search for session information matching the emotion information and display the session information; The screening module is used to screen the session information according to the historical feedback information of the opposite end user corresponding to the local end user on the session information.

7. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the information recommendation method as described in any one of method claims 1-5.

8. An electronic device, characterized in that: The system comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: Get session scenario information; Performing user emotion analysis based on the conversation scenario information to determine corresponding emotion information; the emotion information includes: emotion information of the user at the local end and emotion information of the user at the other end; Searching for session information matching the emotion information, and displaying the session information; The session information is filtered according to historical feedback information of the opposite end user corresponding to the local end user with respect to the session information.

Images