Information recommendation method, device and electronic device

Abstract

The embodiment of the present invention provides an information recommendation method, device and electronic device, wherein the method comprises: obtaining context information in a communication interface, the context information comprising local information and peer information; matching corresponding conversation information from a dialogue library according to the context information, the conversation information being used to guide the peer to interact; and displaying the conversation information. Then, when the user needs to continue the conversation, the user can directly select the conversation information to reply, without the need for the user to manually input word by word and to think about it, 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 information sent by the other party, which is convenient for users to reply; for example, the other party sends a message "Are you free tonight?", and the input method recommends "Free", "Not free", etc., and the local end can choose any recommended information to reply. However, the input method can only recommend information for replying to the other party's message. For example, based on the above example, the local end sends the message "Not free", and the input method of the other end will recommend the message "Okay". When the other end chooses the recommended information to reply, the chat conversation is likely to terminate; which will cause an awkward chat scene, which is not conducive to the continued advancement of the conversation. If the user wants to continue the chat conversation, he needs to manually enter the sentence he wants to reply, such as "What about the weekend?", which is cumbersome and has low input efficiency. Summary of the invention

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

[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 context information in a communication interface, wherein the context information includes local information and peer information; matching corresponding session information from a dialog library based on the context information, wherein the session information is used to guide the peer to interact; and displaying the session information.

[0007] Optionally, obtaining the above information in the communication interface includes: obtaining the chat record corresponding to the communication interface; selecting the last M pieces of peer information in the chat record, and selecting the last M pieces of local information in the chat record, where M is a positive integer.

[0008] Optionally, the dialog library includes multiple dialogs, and matching corresponding session information from the dialog library according to the above information includes:

[0009] The local end information and the opposite end information are matched with each dialogue in the dialogue library respectively to determine at least one target dialogue, wherein the target dialogue matches the local end information and the opposite end information; and the session information is determined according to the target dialogue.

[0010] Optionally, there are multiple target conversations, and determining the session information based on the target conversations includes: sorting the target conversations according to the frequency of each target conversation; and determining the session information based on top N target conversations with the highest frequency, where N is a positive integer.

[0011] Optionally, the conversation includes multiple statements from at least two ends, the target conversation is one, and determining the session information based on the target conversation includes: determining other statements in the target conversation, the other statements including statements in the target conversation except statements matched by the local end information and statements matched by the opposite end information; and using the other statements as session information.

[0012] Optionally, the matching of the local information and the opposite end information with each dialogue in the dialogue library includes at least one of the following methods: sentence matching of the local information and the opposite end information with each dialogue in the dialogue library; semantic matching of the local information and the opposite end information with each dialogue in the dialogue library; pattern matching of the local information and the opposite end information with each dialogue in the dialogue library.

[0013] Optionally, the method further includes the step of generating a dialogue library: collecting a plurality of dialogues, wherein the dialogues include a plurality of statements from at least two ends; counting the frequency corresponding to each dialogue, and generating a dialogue library using each dialogue and the corresponding frequency.

[0014] The embodiment of the present invention also discloses an information recommendation device, which specifically includes: an information acquisition module, which is used to obtain context information in a communication interface, wherein the context information includes local information and peer information; an information matching module, which is used to match corresponding session information from a dialogue library based on the context information, wherein the session information is used to guide the peer to interact; and an information display module, which displays the session information.

[0015] Optionally, the information acquisition module is specifically used to obtain the chat record corresponding to the communication interface; select the last M pieces of peer information in the chat record, and select the last M pieces of local information in the chat record, where M is a positive integer.

[0016] Optionally, the conversation library includes multiple conversations, and the information matching module includes: a conversation matching submodule, used to match the local information and the opposite end information with each conversation in the conversation library respectively, and determine at least one target conversation, wherein the target conversation matches the local information and the opposite end information; an information determination submodule, used to determine session information based on the target conversation.

[0017] Optionally, the information determination submodule is specifically used to sort the target conversations according to the frequency of each target conversation when there are multiple target conversations; and determine the session information according to the top N target conversations with the highest frequency, where N is a positive integer.

[0018] Optionally, the conversation includes multiple statements from at least two ends, and the information determination submodule is specifically used to determine other statements in the target conversation when the target conversation is one, and the other statements include statements in the target conversation except for statements matched by the local end information and statements matched by the opposite end information; and use the other statements as session information.

[0019] Optionally, the conversation matching submodule is specifically used to perform sentence matching on the local information and the other party information with each conversation in the conversation library; and / or, perform semantic matching on the local information and the other party information with each conversation in the conversation library; and / or, perform pattern matching on the local information and the other party information with each conversation in the conversation library.

[0020] Optionally, it also includes: a dialogue generation module, which is used to collect multiple dialogues, wherein the dialogues include multiple statements at least at two ends; count the frequency corresponding to each dialogue, and use each dialogue and the corresponding frequency to generate a dialogue library.

[0021] 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.

[0022] 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 context information in a communication interface, wherein the context information includes local information and opposite end information; matching corresponding session information from a dialog library based on the context information, wherein the session information is used to guide the opposite end to interact; and displaying the session information.

[0023] Optionally, obtaining the above information in the communication interface includes: obtaining the chat record corresponding to the communication interface; selecting the last M pieces of peer information in the chat record, and selecting the last M pieces of local information in the chat record, where M is a positive integer.

[0024] Optionally, the dialog library includes multiple dialogs, and matching corresponding session information from the dialog library based on the above information includes: matching the local information and the opposite end information with each dialog in the dialog library respectively to determine at least one target dialog, wherein the target dialog matches the local information and the opposite end information; and determining the session information based on the target dialog.

[0025] Optionally, there are multiple target conversations, and determining the session information based on the target conversations includes: sorting the target conversations according to the frequency of each target conversation; and determining the session information based on top N target conversations with the highest frequency, where N is a positive integer.

[0026] Optionally, the conversation includes multiple statements from at least two ends, the target conversation is one, and determining the session information based on the target conversation includes: determining other statements in the target conversation, the other statements including statements in the target conversation except statements matched by the local end information and statements matched by the opposite end information; and using the other statements as session information.

[0027] Optionally, the matching of the local information and the opposite end information with each dialogue in the dialogue library includes at least one of the following methods: sentence matching of the local information and the opposite end information with each dialogue in the dialogue library; semantic matching of the local information and the opposite end information with each dialogue in the dialogue library; pattern matching of the local information and the opposite end information with each dialogue in the dialogue library.

[0028] Optionally, it also includes instructions for generating a dialogue library as follows: collecting multiple dialogues, wherein the dialogues include multiple statements from at least two ends; counting the frequency corresponding to each dialogue, and generating a dialogue library using each dialogue and the corresponding frequency.

[0029] The embodiments of the present invention include the following advantages:

[0030] In an embodiment of the present invention, the above information can be obtained in the communication interface, and then the corresponding session information can be matched and displayed from the dialogue library based on the above information, wherein the session information is used to guide the other party to interact; and then when the user needs to continue the conversation, the session information can be directly selected for reply without the user having to manually input word by word and think about it, thereby improving input efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flowchart of steps of an information recommendation method embodiment of the present invention;

[0032] Figure 2 is a flowchart of steps of an optional embodiment of an information recommendation method of the present invention;

[0033] Figure 3 is a structural block diagram of an embodiment of an information recommendation device of the present invention;

[0034] Figure 4 is a structural block diagram of an optional embodiment of an information recommendation device of the present invention;

[0035] Figure 5 A structural block diagram of an electronic device for information recommendation according to an exemplary embodiment;

[0036] 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

[0037] 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.

[0038] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0039] One of the core concepts of the embodiment of the present invention is to recommend, based on the above information, conversation information that can guide the other party to interact, so that when the user needs to continue the conversation, he can directly select the conversation information to reply, thereby improving the efficiency of information input.

[0040] Reference Figure 1 , shows a flowchart of an information recommendation method embodiment of the present invention, which may specifically include the following steps:

[0041] Step 102: Acquire the above information in the communication interface, where the above information includes local end information and peer end information.

[0042] In an embodiment of the present invention, a user can enter a communication interface corresponding to a communication application according to his or her own needs to communicate with other users. The communication application can be an instant messaging application such as a social software, or a short message application; correspondingly, the communication interface can be a chat window of an instant messaging application, or an editing interface of a short message application. Therefore, when a user enters the communication interface of a terminal device to talk with other users, after receiving information from the other end, the context information in the communication interface can be obtained to recommend corresponding reply information to the user based on the context information. The context information can include local information and opposite end information; wherein, there are multiple ways to obtain the context information, such as obtaining through an input method, or obtaining through OCR (Optical Character Recognition) analysis, etc.

[0043] Step 104: According to the above information, the corresponding session information is matched from the dialogue library, and the session information is used to guide the other end to interact.

[0044] In an embodiment of the present invention, conversation information can be recommended to a user, and the conversation information can be used to guide the other end to interact; and then when the user selects the conversation information to reply to the other end, the other end can be guided to interact, such as guiding the other end to reply, so that the conversation continues. In an embodiment of the present invention, multiple conversations can be collected in advance, and a conversation library can be generated using the collected multiple conversations; and then the corresponding conversation information can be matched from the conversation library for the above information; wherein the conversation information can be all information that can guide the other end to interact, such as text such as questions, declarative sentences (such as sentences that raise new topics), etc., and pictures such as emoticon pictures.

[0045] Step 106: Display the session information.

[0046] Then the session information can be displayed, wherein the area for displaying the session information can be set as required, 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, and the present invention is not limited to this; wherein, the displayed session information can be one or more.

[0047] Then the user can select the conversation information that meets his needs from the displayed conversation information to reply and keep the conversation going. The user can perform the on-screen operation and select the corresponding conversation information to reply. For example, after the input method receives the on-screen instruction corresponding to the on-screen operation, the corresponding conversation information can be put on the screen to the edit box of the communication application. After the user performs the send operation, the conversation information can be sent to reply; for another example, after receiving the on-screen instruction corresponding to the on-screen operation, the corresponding conversation information can be directly sent to reply.

[0048] As an example of the present invention, user A enters chat application X to chat with user B. After user A sends the message "Are you free tomorrow?", user B replies "No time". At this time, the input method of the corresponding terminal device of user A can obtain the above information, such as the local information: "Are you free tomorrow?" and the other party information "No time"; then the corresponding session information can be matched from the dialogue library, such as "What about the day after tomorrow?" and "What about the weekend?", and then the two session information are displayed. If user A selects the session information "What about the day after tomorrow?" to reply, user B will reply to this question, such as "I am not free the day after tomorrow either, how about the weekend?", so that the dialogue continues.

[0049] As another example of the present invention, user C enters chat application Y to chat with user D. After user C sends a message "Let's go to a movie together at 8 pm?", user D replies "No, I haven't gotten off work or eaten yet". At this time, the input method of the corresponding terminal device of user C can obtain the above information, such as the local information: "Let's go to a movie together at 8 pm?" and the other-end information "No, I haven't gotten off work or eaten yet"; then the corresponding session information can be matched from the dialogue library, such as "Then I'll treat you to a meal when you get off work", "There is a delicious restaurant nearby, I'll take you there when you get off work", "Then let's go to the cinema for dinner first, and then go to the movies after dinner", "Then let's go together on the weekend?", and display it. If user C selects the session information "There is a delicious restaurant nearby, I'll take you there when you get off work" to reply, user D will reply to this question, such as "Great, what kind of food is that restaurant?", so that the dialogue continues.

[0050] In an embodiment of the present invention, the above information can be obtained in the communication interface, and then the corresponding session information can be matched and displayed from the dialogue library based on the above information, wherein the session information is used to guide the other party to interact; and then when the user needs to continue the conversation, the session information can be directly selected for reply without manual word-by-word input, thereby improving input efficiency.

[0051] In another embodiment of the present invention, a dialog library may be pre-generated, and then the corresponding session information may be matched from the pre-generated dialog library according to the above information.

[0052] The step of generating a dialogue library may include: collecting a plurality of dialogues, wherein the dialogues include a plurality of statements at least at two ends; counting the frequency corresponding to each dialogue, and generating a dialogue library using each dialogue and the corresponding frequency.

[0053] In the embodiment of the present invention, there are multiple ways to collect conversations, such as collecting conversations from various platforms such as social networking sites; collecting chat records from the communication application of the terminal device, and determining the conversations based on the chat records, etc. Among them, the chat records of a set time period can be collected from the communication application of the terminal device, and the set time period can be set according to the needs, such as three months, and then at least one conversation can be determined for the chat records corresponding to each terminal device. Among them, at least one conversation corresponding to the chat record can be determined based on the time corresponding to each statement in the chat record; for example, if the interval between a statement and the previous statement exceeds a set interval (the set interval can be set as one day according to needs), this statement can be regarded as the beginning of a conversation, and then the time interval between the first statement after this statement and the second statement after this statement is determined. If the time interval between the two does not exceed the set interval, the time interval between the second statement after this statement and the third statement after this statement can be determined. If the time interval between the two does not exceed the set interval, the time interval between the third statement after this statement and the fourth statement after this statement can be determined, and so on; until the time interval between two statements exceeds the set interval, the first statement of the two statements can be determined as the end statement of this conversation, and the second statement can be determined as the start statement of another conversation.

[0054] In the embodiment of the present invention, there may be some conversations in which all the statements belong to the same end, and the session information recommended to the user may be information for guiding the other end to interact, such as information for replying to the information of the other end, or information for guiding the other end to reply; if there are only statements from the same end in the conversation, these statements may not be able to guide the other end to interact, so the conversations in which all the statements belong to the same end can be filtered out, and the conversations including multiple statements from at least two ends can be retained. Then the corresponding frequency of each conversation after filtering can be determined, wherein two conversations whose matching degree reaches a set threshold can be regarded as the same conversation, and the set threshold can be set to 80% according to the demand. Among them, the statements in the two conversations can be matched respectively, and the matching degree of the statements in the two conversations can be used as the matching degree of the two conversations. For example, if conversation A has 10 statements and conversation B has 10 statements, and 8 statements of conversation A and conversation B are matched, it can be determined that the matching degree of conversation A and conversation B is 80%. Then a conversation library can be generated according to each conversation and the corresponding frequency.

[0055] Of course, after filtering the dialogues as above and before generating the dialogue library, the filtered dialogues can be further filtered to ensure that the session information matched from each dialogue in the dialogue library can guide the other end to interact; wherein, each dialogue has an ending statement such as the last few statements, and the ending statement is used to end the dialogue; therefore, for each filtered dialogue, the ending statement of this dialogue, such as the last two statements, can be determined, and then the ending statement in this dialogue can be deleted, thereby further filtering each filtered dialogue. For example, dialogue 1: user A: "Are you free tomorrow?", user B: "No time", user A: "What about the weekend?", user B: "No problem". In this dialogue, it can be determined that "No problem" is the ending statement, so "No problem" in dialogue 1 can be deleted, that is, the filtered dialogue 1: user A: "Are you free tomorrow?", user B: "No time", user A: "What about the weekend?"; wherein, after generating the dialogue library, the statements in each dialogue may not include the information of the end to which the statement belongs, for example, dialogue 1 in the dialogue library is: "Are you free tomorrow?", "No time", "What about the weekend?".

[0056] In another embodiment of the present invention, the dialog library may include multiple dialogs, and the above information may be matched with each dialog in the dialog library to determine the corresponding session information.

[0057] 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:

[0058] Step 202: Obtain the chat record corresponding to the communication interface.

[0059] Step 204: Select the last M pieces of peer-end information in the chat record, and select the last M pieces of local-end information in the chat record.

[0060] In an embodiment of the present invention, a user may use an instant messaging application or a short message application to interact with information. During the interaction, the interaction information may be displayed in the communication interface of the current communication application. When the terminal device is in the communication interface of a communication application and receives a message from the other end, the above information in the communication interface may be obtained; wherein, the chat record corresponding to the communication interface may be obtained, and then the above information may be selected 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, which may be set as required, such as 1 hour or 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 chat record to the input method. Then, after the input method receives the chat record, it may determine which is the other end information and which is the local end information. Among them, some users are accustomed to replying a complete content as a message, and some users are accustomed to splitting a complete content into multiple messages for replying. Therefore, the opposite-end message and the local-end message can be analyzed separately, and the last M messages in the opposite-end message (local-end message) are analyzed for relevance, and the relevance score of each message with the last message is determined (the relevance score can be proportional to the relevance); then the last message and other messages with relevance scores exceeding the relevance threshold are selected from the M messages, wherein the relevance threshold can be set as required, and M is a positive integer. When there are more than one messages with relevance scores exceeding the relevance threshold, the last multiple opposite-end messages in the chat record can be selected, and multiple local messages in the chat record can be selected; when there is no message with a relevance score exceeding the relevance threshold, the last opposite-end message in the chat record can be selected, and the last local-end message in the chat record can be selected; then the selected local-end information and the opposite-end information can be used as the above information.

[0061] Step 206: Match the local end information and the opposite end information with each dialog in the dialog library respectively to determine at least one target dialog, wherein the target dialog matches the local end information and matches the opposite end information.

[0062] Then, the corresponding conversation information can be matched for the above information from the pre-generated dialogue library, wherein the local information and the opposite information can be matched with each dialogue in the dialogue library respectively, and at least one target dialogue that matches both the local information and the opposite information is searched; wherein, if there is a sentence matching the local information in a dialogue, and there is a sentence matching the opposite information, the dialogue can be determined as the target dialogue. In the embodiment of the present invention, the manner of matching the local information and the opposite information with each dialogue in the dialogue library respectively may include multiple methods:

[0063] As an example of the present invention, the local information and the opposite information can be sentence matched with each dialogue in the dialogue library. For each dialogue in the dialogue library, sentence matching is performed on each sentence in the dialogue with the local information (which can be a sentence), and the sentence matching with the local information in the dialogue is searched; and the sentence in the dialogue is sentence matched with the opposite information (which can be a sentence), and the sentence matching with the opposite information in the dialogue is searched. For example, dialogue 2 includes the sentences: "Are you free tomorrow night?", "No time", "What about the night after tomorrow?", "No time either", "Are you free on the weekend?", "Yes, yes", "Then let's go to the movies on the weekend", the local information is: "Are you free tomorrow night?", and the opposite information is "No time", the local sentence can be matched with each sentence in dialogue 2 to obtain the sentence matching with the local information: "Are you free tomorrow night?"; and the opposite sentence can be matched with each sentence in dialogue 2 to obtain the sentence matching with the local information: "No time", and then it is determined that dialogue 2 is the target sentence.

[0064] As another example of the present invention, the local information and the peer information can be semantically matched with each dialogue in the dialogue library. The local information and the peer information can be semantically analyzed to determine the semantics corresponding to the local information and the semantics corresponding to the peer information, and then for each dialogue, the semantics of each dialogue in the dialogue are matched with the semantics of the peer information, and the semantics of each dialogue in the dialogue are matched with the semantics of the peer information to determine the target sentence.

[0065] As another example of the present invention, the local information and the opposite information can be pattern matched with each dialogue in the dialogue library. Among them, the pattern of the local information and the opposite information can be determined respectively, and then for each dialogue, the pattern of each dialogue in the dialogue is matched with the pattern of the opposite information respectively, and the pattern of each dialogue in the dialogue is matched with the pattern of the opposite information respectively, to determine the target sentence. For example, the local information: "Are you free today?" can determine that the corresponding pattern is: "Are you free ** (time)?", and the opposite information: "Not free today", it is determined that the corresponding pattern can be: "** (time) not free", and then the pattern "Are you free ** (time)?" is used to match the pattern of each sentence in the dialogue, and the pattern "** (time) not free" is used to match the pattern of each sentence in the dialogue; if there is a sentence in the dialogue with the pattern of "Are you free ** (time)?", and there is a sentence with the pattern of "** (time) not free", it can be determined that the dialogue is the target dialogue.

[0066] Step 208: Determine session information according to the target dialogue.

[0067] In the embodiment of the present invention, the determined target dialogue may be one or more. If the target dialogue is one, determining the session information according to the target dialogue may include the following sub-steps:

[0068] Sub-step 82: determining other sentences in the target dialogue, wherein the other sentences include sentences in the target dialogue except the sentences matched by the local end information and the sentences matched by the opposite end information.

[0069] Sub-step 84: Use the other statements as session information.

[0070] In the embodiment of the present invention, other statements in the target dialogue can be determined, and then session information can be selected from the other statements, wherein all other statements can be used as session information, or some other statements can be selected as session information according to a set rule, and the set rule can be set according to demand, for example, M statements after the statement matching the peer information are selected as session information, wherein M is an integer greater than 0. The other statements include statements in the target dialogue except the statements matching the local information and the statements matching the peer information.

[0071] If there are multiple target conversations, determining the session information according to the target conversations may include the following sub-steps:

[0072] Sub-step 92: sorting the target dialogues according to the frequencies of the target dialogues.

[0073] Sub-step 94: Determine the session information based on the top N target conversations with the highest frequency, where N is an integer greater than 0.

[0074] In the embodiment of the present invention, when there are multiple target dialogues, some of the target dialogues can be selected from the multiple target dialogues, and then the session information can be determined based on the selected target dialogues; wherein, the target dialogues can be sorted according to the frequency of each target dialogue, and then the top N target dialogues with the highest frequency can be selected, and the session information can be determined based on the N target dialogues. wherein, the session information can be selected from other sentences of the N target dialogues respectively, and the selection method is similar to the above, and will not be repeated here.

[0075] Step 210: Display the session information.

[0076] Then the conversation information can be displayed for user selection; wherein, in the process of displaying the conversation information, if the target conversation is determined to be one and multiple other sentences are selected as the conversation information, the conversation information can be displayed in the order of the other sentences in the target conversation; if the target conversation is determined to be multiple, the conversation information corresponding to each target conversation can be displayed according to the frequency of the target conversation, for example, the display position of the conversation information corresponding to the target conversation with a high frequency can be arranged before the display position of the conversation information corresponding to the target conversation with a low frequency. Furthermore, when the user wants to continue the conversation, he can directly search for the conversation information that meets the needs from the displayed conversation information, and then select the conversation information that meets the needs and send it, which improves the efficiency of information input.

[0077] In an optional embodiment of the present invention, before displaying the session information, the session information can be analyzed to obtain the associated information corresponding to the session information, and then the session information can be modified by combining the associated information, the peer information and the local information, and then the modified session information can be displayed; thereby improving the accuracy of the input method recommendation session information, better meeting the user's needs, and further improving the input efficiency. Among them, the associated information can include time information, location information, etc., and of course can also include other information, which is not limited by the embodiment of the present invention. For example, user A sends a message to user B "Are you free tomorrow?", and user B replies "No time", and the input method of user A can determine the session information "How about the weekend?" based on "Are you free tomorrow?" and "No time"; at this time, the session information is analyzed to determine that the session information is related to time, and then the time information such as "Friday" can be obtained; then combined with the local information "Are you free tomorrow?" and the time information "Friday", it can be determined that tomorrow is Saturday, so "How about the weekend" can be modified to "How about Sunday?", and then the modified session information is displayed. For another example, user A sends a message to user B, "Have you gotten off work?", user B replies, "Just got off work", user A: "Have you eaten yet?", user B: "No", user A's input method can determine the session information "Will you come to my place for dinner?" based on "Have you eaten yet?" and "No"; at this time, the session information is analyzed to determine that the session information is related to the location, and the location information such as "** restaurant" can be obtained; then the session information can be modified based on the location information, such as modifying it to "Will you come to ** restaurant for dinner?", and then display the modified session information.

[0078] In an embodiment of the present invention, the above information can be obtained in the communication interface, and then the corresponding session information can be matched and displayed from the dialogue library based on the above information, wherein the session information is used to guide the other party to interact; and then when the user needs to continue the conversation, the session information can be directly selected for reply without manual word-by-word input, thereby improving input efficiency.

[0079] Secondly, in the embodiment of the present invention, if there are multiple target conversations, determining the conversation information according to the target conversations may include: sorting the target conversations according to the frequency of each target conversation; and determining the conversation information according to the top N target conversations with the highest frequency, where N is an integer greater than 0. This can make the conversation information more consistent with the user's intention, improve the user experience, and further improve the input efficiency.

[0080] 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.

[0081] Reference Figure 3 , shows a structural block diagram of an embodiment of an information recommendation device of the present invention, which may specifically include the following modules: an information acquisition module 302, an information matching module 304 and an information display module 306, wherein:

[0082] The information acquisition module 302 is used to acquire the above information in the communication interface, wherein the above information includes local end information and peer end information;

[0083] An information matching module 304 is used to match corresponding session information from a dialog library according to the above information, wherein the session information is used to guide the other end to interact;

[0084] The information display module 306 displays the session information.

[0085] Reference Figure 4 , showing a structural block diagram of an optional embodiment of an information recommendation device of the present invention. In an optional embodiment of the present invention, the device further includes: a dialogue generation module 308, which is used to collect multiple dialogues, wherein the dialogues include multiple statements at least at two ends; count the frequencies corresponding to each dialogue, and use each dialogue and the corresponding frequencies to generate a dialogue library.

[0086] In an optional embodiment of the present invention, the information acquisition module 302 is specifically used to obtain the chat record corresponding to the communication interface; select the last M pieces of peer information in the chat record, and select the last M pieces of local information in the chat record, where M is a positive integer.

[0087] In an optional embodiment of the present invention, the dialogue library includes multiple dialogues, and the information matching module 304 includes: a dialogue matching submodule 3042 and an information determination submodule 3044, wherein:

[0088] A conversation matching submodule 3042 is used to match the local end information and the opposite end information with each conversation in the conversation library, and determine at least one target conversation, wherein the target conversation matches the local end information and the opposite end information;

[0089] The information determination submodule 3044 is used to determine the session information according to the target dialogue.

[0090] In an optional embodiment of the present invention, the information determination submodule 3044 is specifically used to sort the target conversations according to the frequency of each target conversation when there are multiple target conversations; and determine the session information according to the top N target conversations with the highest frequency, where N is a positive integer.

[0091] In an optional embodiment of the present invention, the dialogue includes at least a plurality of statements from both ends.

[0092] The information determination submodule 3044 is specifically used to determine other statements in the target dialogue when there is one target dialogue, wherein the other statements include statements in the target dialogue except the statements matched by the local information and the statements matched by the opposite end information; and use the other statements as session information.

[0093] In an optional embodiment of the present invention, the conversation matching submodule 3042 is specifically used to perform sentence matching between the local information and the opposite information and each conversation in the conversation library; and / or, perform semantic matching between the local information and the opposite information and each conversation in the conversation library; and / or, perform pattern matching between the local information and the opposite information and each conversation in the conversation library.

[0094] In an embodiment of the present invention, the above information can be obtained in the communication interface, and then the corresponding session information can be matched and displayed from the dialogue library based on the above information, wherein the session information is used to guide the other party to interact; and then when the user needs to continue the conversation, the session information can be directly selected for reply without manual word-by-word input, thereby improving input efficiency.

[0095] 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.

[0096] 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.

[0097] 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 .

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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 context information in a communication interface, the context information comprising local information and opposite end information; matching corresponding session information from a dialogue library based on the context information, the session information being used to guide the opposite end to interact; and displaying the session information.

[0109] Optionally, obtaining the above information in the communication interface includes: obtaining the chat record corresponding to the communication interface; selecting the last M pieces of peer information in the chat record, and selecting the last M pieces of local information in the chat record, where M is a positive integer.

[0110] Optionally, the dialog library includes multiple dialogs, and matching corresponding session information from the dialog library according to the above information includes:

[0111] The local end information and the opposite end information are matched with each dialogue in the dialogue library respectively to determine at least one target dialogue, wherein the target dialogue matches the local end information and the opposite end information; and the session information is determined according to the target dialogue.

[0112] Optionally, there are multiple target conversations, and determining the session information based on the target conversations includes: sorting the target conversations according to the frequency of each target conversation; and determining the session information based on top N target conversations with the highest frequency, where N is a positive integer.

[0113] Optionally, the conversation includes multiple statements from at least two ends, the target conversation is one, and determining the session information based on the target conversation includes: determining other statements in the target conversation, the other statements including statements in the target conversation except statements matched by the local end information and statements matched by the opposite end information; and using the other statements as session information.

[0114] Optionally, the matching of the local information and the opposite end information with each dialogue in the dialogue library includes at least one of the following methods: sentence matching of the local information and the opposite end information with each dialogue in the dialogue library; semantic matching of the local information and the opposite end information with each dialogue in the dialogue library; pattern matching of the local information and the opposite end information with each dialogue in the dialogue library.

[0115] Optionally, the method further includes the step of generating a dialogue library: collecting a plurality of dialogues, wherein the dialogues include a plurality of statements from at least two ends; counting the frequency corresponding to each dialogue, and generating a dialogue library using each dialogue and the corresponding frequency.

[0116] 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.

[0117] 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.

[0118] 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 context information in a communication interface, wherein the context information includes local information and opposite end information; matching corresponding session information from a dialogue library based on the context information, wherein the session information is used to guide the opposite end to interact; and displaying the session information.

[0119] Optionally, obtaining the above information in the communication interface includes: obtaining the chat record corresponding to the communication interface; selecting the last M pieces of peer information in the chat record, and selecting the last M pieces of local information in the chat record, where M is a positive integer.

[0120] Optionally, the dialog library includes multiple dialogs, and matching corresponding session information from the dialog library based on the above information includes: matching the local information and the opposite end information with each dialog in the dialog library respectively to determine at least one target dialog, wherein the target dialog matches the local information and the opposite end information; and determining the session information based on the target dialog.

[0121] Optionally, there are multiple target conversations, and determining the session information based on the target conversations includes: sorting the target conversations according to the frequency of each target conversation; and determining the session information based on top N target conversations with the highest frequency, where N is a positive integer.

[0122] Optionally, the conversation includes multiple statements from at least two ends, the target conversation is one, and determining the session information based on the target conversation includes: determining other statements in the target conversation, the other statements including statements in the target conversation except statements matched by the local end information and statements matched by the opposite end information; and using the other statements as session information.

[0123] Optionally, the matching of the local information and the opposite end information with each dialogue in the dialogue library includes at least one of the following methods: sentence matching of the local information and the opposite end information with each dialogue in the dialogue library; semantic matching of the local information and the opposite end information with each dialogue in the dialogue library; pattern matching of the local information and the opposite end information with each dialogue in the dialogue library.

[0124] Optionally, it also includes instructions for generating a dialogue library as follows: collecting multiple dialogues, wherein the dialogues include multiple statements from at least two ends; counting the frequency corresponding to each dialogue, and generating a dialogue library using each dialogue and the corresponding frequency.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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 A step that specifies a function in one or more boxes.

[0129] 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.

[0130] 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.

[0131] 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: Obtain chat records in the communication interface, select the last M pieces of peer information and the last M pieces of local information in the chat records, where M is a positive integer; Relevance analysis is performed on the M pieces of peer-end information and the M pieces of local-end information respectively, and a relevance score between other pieces of information except the last piece of information in the M pieces of information and the last piece of information is determined, wherein the relevance score is proportional to the relevance; the M pieces of information indicate the M pieces of peer-end information or the M pieces of local-end information for which relevance analysis is performed; When there are more than one other information whose relevance score exceeds the relevance threshold, select the other information whose relevance score exceeds the relevance threshold from the M pieces of information; when there is no other information whose relevance score exceeds the relevance threshold, select the last piece of information from the M pieces of information; wherein the information selected from the M pieces of information can constitute one piece of information with complete meaning; The selected information is used as the above information; For the above information, the local end information and the opposite end information are matched with each dialogue in the dialogue library respectively to determine at least one target dialogue; wherein the dialogue library includes multiple dialogues, each dialogue includes multiple statements from at least two ends, and the dialogue does not include an ending statement, the ending statement is used to end the dialogue, and the time interval between adjacent statements included in each dialogue does not exceed a set interval; the target dialogue matches the local end information and the opposite end information; When there are multiple target conversations, sort the target conversations according to their frequencies; determine the conversation information according to the top N target conversations with the highest frequencies; N is a positive integer, and the conversation information is used to guide the other end to interact so that the conversation between the local end and the other end continues; When there is only one target dialogue, other sentences in the target dialogue except the sentences matched by the local end information and the sentences matched by the peer end information are used as the session information; Acquire association information corresponding to the session information, the association information including at least one of time information and location information, the time information indicating the current time of the local user, and the location information indicating the current location of the local user; The session information is modified in combination with the association information, the peer information and the local information in the above information; and the modified session information is displayed.

2. The method according to claim 1, characterized in that The matching of the local end information and the peer end information with each conversation in the conversation library includes at least one of the following methods: Matching the local end information and the peer end information with each dialogue in the dialogue library respectively; Semantically matching the local end information and the peer end information with each conversation in the conversation library; The local end information and the opposite end information are pattern matched with each dialogue in the dialogue library respectively.

3. The method according to claim 1, characterized in that The step of generating the dialog library is also included: Collect multiple conversations; The frequencies corresponding to the dialogues are counted, and the dialogue library is generated using the dialogues and the corresponding frequencies.

4. An information recommendation device, characterized in that: include: An information acquisition module, used to acquire a chat record in a communication interface, select the last M pieces of peer-end information and the last M pieces of local-end information in the chat record, where M is a positive integer; perform relevance analysis on the M pieces of peer-end information and the M pieces of local-end information respectively, and determine the relevance score between other information in the M pieces of information except the last piece of information and the last piece of information, wherein the relevance score is proportional to the relevance; the M pieces of information indicate the M pieces of peer-end information or the M pieces of local-end information for which relevance analysis is performed; when there are more than one piece of other information with a relevance score exceeding a relevance threshold, select the other information with a relevance score exceeding the relevance threshold from the M pieces of information; when there is no other information with a relevance score exceeding the relevance threshold, select the last piece of information from the M pieces of information; wherein the information selected from the M pieces of information can constitute a piece of information with a complete meaning; and the selected information is used as the above information; An information matching module, including a conversation matching submodule and an information determination submodule; The conversation matching submodule is used to match the local end information and the opposite end information with each conversation in the conversation library for the above information, and determine at least one target conversation; wherein the conversation library includes multiple conversations, each conversation includes multiple statements from at least two ends, and the conversation does not include an ending statement, the ending statement is used to end the conversation, and the time interval between adjacent statements included in each conversation does not exceed a set interval; the target conversation matches the local end information and the opposite end information; The information determination submodule is used to sort the target conversations according to the frequency of each target conversation when there are multiple target conversations; determine the session information according to the top N target conversations with the highest frequency; N is a positive integer, and the session information is used to guide the other end to interact so that the conversation between the local end and the other end continues; when there is only one target conversation, use the other sentences in the target conversation except the sentences matched by the local end information and the sentences matched by the other end information as the session information; The information display module is used to obtain the associated information corresponding to the session information, the associated information including at least one of time information and location information, the time information indicating the current time of the local user, and the location information indicating the current location of the local user; modify the session information in combination with the associated information, the peer information in the above information, and the local information; and display the modified session information.

5. The device according to claim 4, characterized in that The conversation matching submodule is specifically used to perform sentence matching between the local information and the opposite information and each conversation in the conversation library; and / or, perform semantic matching between the local information and the opposite information and each conversation in the conversation library; and / or, perform pattern matching between the local information and the opposite information and each conversation in the conversation library.

6. The device according to claim 4, characterized in that Also includes: A dialogue generation module, used to collect multiple dialogues; The frequencies corresponding to the dialogues are counted, and the dialogue library is generated using the dialogues and the corresponding frequencies.

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 1-3.

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: Obtain chat records in the communication interface, select the last M pieces of peer information and the last M pieces of local information in the chat records, where M is a positive integer; Relevance analysis is performed on the M pieces of peer-end information and the M pieces of local-end information respectively, and a relevance score between other pieces of information except the last piece of information in the M pieces of information and the last piece of information is determined, wherein the relevance score is proportional to the relevance; the M pieces of information indicate the M pieces of peer-end information or the M pieces of local-end information for which relevance analysis is performed; When there are more than one other information whose relevance score exceeds the relevance threshold, select the other information whose relevance score exceeds the relevance threshold from the M pieces of information; when there is no other information whose relevance score exceeds the relevance threshold, select the last piece of information from the M pieces of information; wherein the information selected from the M pieces of information can constitute one piece of information with complete meaning; The selected information is used as the above information; For the above information, the local end information and the opposite end information are matched with each dialogue in the dialogue library respectively to determine at least one target dialogue; wherein the dialogue library includes multiple dialogues, each dialogue includes multiple statements from at least two ends, and the dialogue does not include an ending statement, the ending statement is used to end the dialogue, and the time interval between adjacent statements included in each dialogue does not exceed a set interval; the target dialogue matches the local end information and the opposite end information; When there are multiple target conversations, sort the target conversations according to their frequencies; determine the conversation information according to the top N target conversations with the highest frequencies; N is a positive integer, and the conversation information is used to guide the other end to interact so that the conversation between the local end and the other end continues; When there is only one target dialogue, other sentences in the target dialogue except the sentences matched by the local end information and the sentences matched by the peer end information are used as the session information; Acquire association information corresponding to the session information, the association information including at least one of time information and location information, the time information indicating the current time of the local user, and the location information indicating the current location of the local user; The session information is modified in combination with the association information, the peer information and the local information in the above information; and the modified session information is displayed.

9. The electronic device according to claim 8, characterized in that: The matching of the local end information and the peer end information with each conversation in the conversation library includes at least one of the following methods: Matching the local end information and the peer end information with each dialogue in the dialogue library respectively; Semantically matching the local end information and the peer end information with each conversation in the conversation library; The local end information and the opposite end information are pattern matched with each dialogue in the dialogue library respectively.

10. The electronic device according to claim 8, characterized in that: It also contains instructions for generating the dialog library as follows: Collect multiple conversations; The frequencies corresponding to the dialogues are counted, and the dialogue library is generated using the dialogues and the corresponding frequencies.

Images