Recommendation method and device, and device for recommendation
By obtaining and processing communication content, providing beautiful words and intention identification information, the problem of low communication quality caused by language expression limitations in communication applications is solved, and the quality and efficiency of communication content is improved.
Patent Information
- Application Number
- CN201710214846.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2017-04-01
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2037-04-01
AI Technical Summary
In existing communication applications, the quality of communication content input by users is easily limited by language expression ability, resulting in poor communication and communication quality.
By obtaining the user's communication content, extracting the content of beautiful words and intention identification information, providing the content of beautiful words reply, and improving language quality and communication efficiency.
The quality of communication content transmitted to the counterpart users has been improved and the effect of communication and communication has been enhanced.
Smart Images

Figure CN108664336B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of communication technology, and in particular to a recommendation method and device, and a device for recommendation. Background Art
[0002] With the development of communication technology, communication applications such as SMS applications and instant messaging applications have been accepted by more and more users. Taking WeChat application as an example, users can use this instant messaging application to transmit text and other information with their family, friends, colleagues or customers to achieve the function of communication.
[0003] In the existing scheme, a user can input text through an input method application, so that the communication content input through the input method application can be transmitted to the other end user of the communication. However, in actual application, the quality of the communication content transmitted to the other end user is easily limited by factors such as the user's language expression ability, and the quality of the communication content plays a relatively important role in communication. For example, high-quality communication content can promote pleasant communication, and low-quality communication content may cause obstacles to communication. Summary of the invention
[0004] In view of the above problems, embodiments of the present invention are proposed to provide a recommendation method, a recommendation device, and a device for recommendation that overcome the above problems or at least partially solve the above problems. The embodiments of the present invention can.
[0005] In order to solve the above problems, the present invention discloses a recommendation method, comprising:
[0006] Acquire the communication content of the current user; the communication content of the current user includes: the first content input by the current user, and / or the second content received;
[0007] Acquire recommended content corresponding to the communication content; the recommended content includes: compliment content corresponding to the first content, and / or, intention identification information and / or compliment reply content corresponding to the second content;
[0008] The recommended content is output to the current user.
[0009] In another aspect, the present invention discloses a recommendation device, comprising:
[0010] A communication content acquisition module, used to acquire the communication content of the current user; the communication content of the current user includes: the first content input by the current user, and / or the second content received;
[0011] a recommended content acquisition module, configured to acquire recommended content corresponding to the communication content; the recommended content includes: compliment content corresponding to the first content, and / or, intention recognition information and / or compliment reply content corresponding to the second content; and
[0012] The recommended content output module is used to output the recommended content to the current user.
[0013] Optionally, the recommended content acquisition module includes:
[0014] A mode determination submodule, used to determine a target compliment mode corresponding to the first content;
[0015] The conversion submodule is used to convert the first content into compliment content that conforms to the target compliment mode as the compliment content corresponding to the first content.
[0016] Optionally, the mode determination submodule includes:
[0017] a first determining unit, configured to respond to a trigger instruction of the current user and use a flattering mode corresponding to the trigger instruction as a target flattering mode corresponding to the first content; or
[0018] a second determining unit, configured to determine a target compliment pattern corresponding to the first content according to a social relationship between the current user and a peer user corresponding to the first content and / or a historical compliment pattern used; or
[0019] The third determining unit is configured to determine a target compliment mode corresponding to the first content according to the compliment mode used by the current user's interest friends under the first content.
[0020] Optionally, the second determining unit includes:
[0021] a first selection subunit, configured to select, from the historical nicety patterns used between the current user and the opposite user corresponding to the first content, a historical nicety pattern with a usage frequency exceeding a frequency threshold as a target nicety pattern corresponding to the first content; and / or
[0022] The second selection subunit acquires a target sweetness pattern corresponding to the first content from preset sweetness patterns according to a matching degree between a social relationship between the current user and a counterpart user corresponding to the first content and the sweetness pattern.
[0023] Optionally, the trigger instruction is an instruction triggered by the current user through a touch device located on the back or side of the smart terminal; or
[0024] The trigger instruction is a voice instruction triggered by the current user.
[0025] Optionally, the conversion submodule includes:
[0026] A model input unit, configured to input the first content into a target flattery model corresponding to the target flattery model;
[0027] The model output unit is used to use the flattering content output by the target flattering model as the flattering content corresponding to the first content.
[0028] Optionally, the recommended content acquisition module includes:
[0029] The intention identification submodule is used to identify the intention of the opposite user for the second content, and use the obtained intention identification information as the recommended content corresponding to the second content.
[0030] Optionally, the recommended content acquisition module further includes:
[0031] The compliment reply content acquisition submodule is used to acquire the compliment reply content corresponding to the second content according to the intention recognition information as the recommended content corresponding to the second content.
[0032] Optionally, the intention recognition submodule includes:
[0033] The identification unit is used to identify the intention of the opposite user for the second content based on the historical input behavior data and / or psychological knowledge of at least one user in the entire network, so as to obtain corresponding intention identification information.
[0034] Optionally, the submodule for acquiring the content of the nice reply includes:
[0035] The reply rule acquisition unit is used to use the kind reply rule corresponding to the intention recognition information to acquire the kind reply content corresponding to the second content according to the intention recognition information.
[0036] In another aspect, the present invention discloses a device for recommendation, 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. The one or more programs include instructions for performing the following operations:
[0037] Acquire the communication content of the current user; the communication content of the current user includes: the first content input by the current user, and / or the second content received;
[0038] Acquire recommended content corresponding to the communication content; the recommended content includes: compliment content corresponding to the first content, and / or, intention identification information and / or compliment reply content corresponding to the second content;
[0039] The recommended content is output to the current user.
[0040] In yet another aspect, the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes the device to perform one or more of the aforementioned methods.
[0041] The embodiments of the present invention include the following advantages:
[0042] The embodiment of the present invention can output complimenting content corresponding to the first content to the current user. The complimenting content corresponding to the first content can be content corresponding to the first content that has been beautified in the first language, and / or content corresponding to the first content that meets the first preset complimenting condition. Since the above-mentioned first language beautification processing can improve the language quality of the first content, and / or the above-mentioned first preset complimenting condition can constrain the language quality of the complimenting content, the quality of the complimenting content in the embodiment of the present invention can be higher than that of the first content. Therefore, the embodiment of the present invention can improve the quality of the communication content transmitted to the opposite user, and thus can improve the quality of communication exchanges.
[0043] The embodiment of the present invention can output the intention recognition information and / or the compliment reply content corresponding to the second content to the current user; wherein, the above intention recognition information can reflect the real thoughts of the opposite user on the second content, so providing the above intention recognition information to the current user can enable the current user to refer to the intention recognition information to reply to the second content, so as to obtain the reply content with higher quality. The compliment reply content corresponding to the second content can be used to represent the reply content corresponding to the second content that has been beautified in the second language, and / or the reply content corresponding to the second content that meets the second preset compliment condition; since the above second language beautification can improve the language quality of the reply content corresponding to the second content, and / or the above second preset compliment condition can constrain the language quality of the reply content corresponding to the second content, therefore, the embodiment of the present invention can provide the user with compliment reply content without relying on the input of the current user, can improve the efficiency of the current user's reply to the second content, and can improve the quality of the communication content transmitted to the opposite user, thereby improving the quality of communication exchanges. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 is a schematic diagram of an application environment of a recommended method of the present invention;
[0045] Figure 2 is a flowchart of steps of a recommended method embodiment of the present invention;
[0046] Figure 3 is a structural block diagram of a recommended device embodiment of the present invention;
[0047] Figure 4 is a block diagram showing a device for recommendation as a terminal according to an exemplary embodiment;
[0048] Figure 5 is a block diagram showing a device for recommendation as a server according to an exemplary embodiment;
[0049] Figure 6 It is a schematic structural diagram of a protective device 1 and a mobile terminal 2 in a fitted state according to an embodiment of the present invention;
[0050] Figure 7 It is a schematic structural diagram of a protective device 1 and a mobile terminal 2 in a fitted state according to an embodiment of the present invention;
[0051] Figure 8 is a schematic structural diagram of a protection device 1 according to an embodiment of the present invention;
[0052] Fig. 9 1 is a schematic diagram of a rear view of a rear housing 4 according to an embodiment of the present invention;
[0053] Fig.10 1 is a schematic diagram of a rear view of a rear housing 4 according to an embodiment of the present invention;
[0054] Fig.11 1 is a schematic diagram of a rear view of a rear housing 4 according to an embodiment of the present invention;
[0055] Fig.12 1 is a schematic diagram of a rear view of a rear housing 4 according to an embodiment of the present invention;
[0056] Fig.13 is a schematic diagram of a side view of a rear housing 4 according to an embodiment of the present invention;
[0057] Fig.14 FIG. 4 is a schematic diagram of a side view of a rear housing 4 according to an embodiment of the present invention. DETAILED DESCRIPTION
[0058] 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.
[0059] An embodiment of the present invention provides a recommendation scheme, which can obtain the communication content of the current user; the communication content of the current user may include: first content input by the current user, and / or, second content received; obtain recommended content corresponding to the communication content; the recommended content may include: compliment content corresponding to the first content, and / or, compliment reply content corresponding to the second content; output the recommended content to the current user.
[0060] The embodiment of the present invention can output complimenting content corresponding to the first content to the current user. The complimenting content corresponding to the first content can be content corresponding to the first content that has been beautified in the first language, and / or content corresponding to the first content that meets the first preset complimenting condition. Since the above-mentioned first language beautification processing can improve the language quality of the first content, and / or the above-mentioned first preset complimenting condition can constrain the language quality of the complimenting content, the quality of the complimenting content in the embodiment of the present invention can be higher than that of the first content. Therefore, the embodiment of the present invention can improve the quality of the communication content transmitted to the opposite user, and thus can improve the quality of communication exchanges.
[0061] The embodiment of the present invention can output the intention recognition information and / or the compliment reply content corresponding to the second content to the current user; wherein, the above intention recognition information can reflect the real thoughts of the opposite user on the second content, so providing the above intention recognition information to the current user can enable the current user to refer to the intention recognition information to reply to the second content, so as to obtain the reply content with higher quality. The compliment reply content corresponding to the second content can be used to represent the reply content corresponding to the second content that has been beautified in the second language, and / or the reply content corresponding to the second content that meets the second preset compliment condition; since the above second language beautification can improve the language quality of the reply content corresponding to the second content, and / or the above second preset compliment condition can constrain the language quality of the reply content corresponding to the second content, therefore, the embodiment of the present invention can provide the user with compliment reply content without relying on the input of the current user, can improve the efficiency of the current user's reply to the second content, and can improve the quality of the communication content transmitted to the opposite user, thereby improving the quality of communication exchanges.
[0062] Among them, the first language beautification processing and the second language beautification processing are respectively used for language beautification processing of the reply content corresponding to the first content and the second content, so as to obtain high-quality beautification content or beautification reply content respectively. It can be understood that the embodiment of the present invention does not limit the specific first language beautification processing and second language beautification processing processes.
[0063] The embodiments of the present invention can be applied to any application environment of an APP, such as an input method APP (application), a search APP, a browser APP, an instant messaging APP, etc., to improve the quality of the communication content transmitted to the peer user, thereby improving the quality of communication exchanges. In addition, the embodiments of the present invention can be applied to communication exchange scenarios such as instant messaging scenarios. It can be understood that the embodiments of the present invention are not limited to specific application environments and specific application scenarios.
[0064] The recommended method provided in the embodiment of the present invention can be applied to Figure 1 In the application environment shown, Figure 1As shown, the client 100 and the server 200 are located in a wired or wireless network, and the client 100 and the server 200 perform data exchange through the wired or wireless network.
[0065] The recommendation process of the embodiment of the present invention may be executed by either the client 100 or the server 200:
[0066] For example, the client 100 may obtain the communication content of the current user and send the communication content to the server 200 ; after receiving the communication content, the server 200 may obtain the recommended content corresponding to the communication content and output the recommended content to the client 100 .
[0067] Alternatively, the client 100 may obtain the communication content of the user, and obtain the recommended content corresponding to the communication content, and then output the recommended content to the current user.
[0068] Optionally, the client 100 can run on a smart terminal, which specifically includes but is not limited to: smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, car computers, desktop computers, set-top boxes, smart TVs, wearable devices, etc.
[0069] Method Embodiment
[0070] Reference Figure 2 , shows a flowchart of a recommended method embodiment of the present invention, which may specifically include the following steps:
[0071] Step 201: Acquire the communication content of the current user; the communication content of the current user may include: the first content input by the current user, and / or the second content received;
[0072] Step 202: Obtain recommended content corresponding to the communication content; the recommended content may include: compliment content corresponding to the first content, and / or intention identification information and / or compliment reply content corresponding to the second content;
[0073] Step 203: output the recommended content to the current user.
[0074] The embodiments of the present invention can be applied to a client or a server;
[0075] Wherein, in the case of application to a client, the client may obtain the recommended content corresponding to the communication content by executing steps 201-202, and recommend the recommended content to the current user through the smart terminal;
[0076] When applied to a server, the server may receive the communication content of the current user sent by the client through step 201, and the server may obtain the recommended content corresponding to the communication content through step 202, and send the recommended content to the client.
[0077] In an embodiment of the present invention, the peer user may be a user communicating with the current user of the smart terminal (i.e., the local user), wherein the current user and the peer user may communicate through any communication APP with communication function, such as an instant messaging APP, a short message APP, a social networking site APP, etc.
[0078] The client of the embodiment of the present invention can correspond to any APP running on the smart terminal, wherein the APP can be an input method APP, or a news APP, a browser APP, or an instant messaging APP, etc.; wherein the server of the input method APP can collect and maintain the historical input behavior data of at least one user, and optionally, the server of the input method APP can also provide an acquisition interface for the historical input behavior data of the at least one user, so that other APPs can obtain the acquisition interface of the historical input behavior data of the multiple users through the acquisition interface. The embodiment of the present invention mainly takes the input method APP as an example for explanation, and other APPs can refer to each other.
[0079] It should be noted that the current user of the embodiment of the present invention can be identified by a user ID (identification) or by a device ID of a smart terminal. That is, the embodiment of the present invention does not require the user to log in to the corresponding APP through a user ID, and different users can also be identified through a device ID.
[0080] In the communication exchange scenario, the communication content of the current user may include: the first content input by the current user, and / or, the second content received. Optionally, step 201 may obtain the first content input by the current user through an APP such as an input method APP; and / or, step 201 may obtain the second content received through a communication APP, for example, the second content may come from a peer user, and the peer user may be a user of a communication APP or even a user of a social networking site, etc. It can be understood that the embodiment of the present invention does not limit the specific process of obtaining the communication content of the current user in step 201.
[0081] In the case that the communication content of the current user includes the first content, the embodiment of the present invention can obtain the compliment content corresponding to the first content. The compliment content corresponding to the first content can be the content corresponding to the first content that has been beautified in the first language, and / or the content corresponding to the first content that meets the first preset compliment condition. Since the above-mentioned first language beautification processing can improve the language quality of the first content, and / or the above-mentioned first preset compliment condition can constrain the language quality of the compliment content, the quality of the compliment content in the embodiment of the present invention can be higher than that of the first content.
[0082] In an application example 1 of the present invention, it is assumed that the first content is the reply content of the second content, and it is assumed that the second content and the first content are "We discussed it and finally decided to use the first draft" and "Received, thank you" respectively. In this case, the language corresponding to the first content "Received, thank you" is relatively mediocre, and the embodiment of the present invention can obtain the compliment content corresponding to the first content "Dear customer, you have a really great vision", so that the quality of the communication content transmitted to the opposite user can be improved, and then the opposite user's good impression and evaluation of the local user can be improved. It can be understood that the above-mentioned first content is the reply content of the second content only as an example of a communication exchange scenario. In fact, the above-mentioned first content can be the content input by the current user when the second content does not exist. One purpose of the embodiment of the present invention is to improve the language quality of the first content, and the specific scenario of the first content is not limited.
[0083] In an optional embodiment of the present invention, the process of obtaining the recommended content corresponding to the communication content in step 202 may include: determining a target compliment pattern corresponding to the first content; and converting the first content into compliment content that conforms to the target compliment pattern as the compliment content corresponding to the first content.
[0084] The beautification mode may be used to indicate language beautification processing and / or a standard style corresponding to a language beautification effect. In actual application, at least one compliment mode can be pre-set, for example, the pre-acquired compliment modes may include: super manager compliment mode, poetry life compliment mode, dream goddess compliment mode, sweet talk compliment mode, etc.; wherein, the opposite-end users corresponding to the super manager compliment mode may include: customers, etc., who can use reasonable language skills to praise customers, so that the mediocre first content can be converted into compliment content with, for example, natural and sincere characteristics; the opposite-end users corresponding to the poetry life compliment mode may include: friends, etc., who can use reasonable language skills to organize compliment content with poetic and literary characteristics, that is, the mediocre first content can be converted into compliment content with, for example, poetic and literary characteristics; the opposite-end users corresponding to the dream goddess compliment mode may include: the goddess being pursued, etc., who can use reasonable language skills to communicate with the goddess to make the goddess happy, so that the mediocre first content can be converted into, for example, considerate compliment content; the opposite-end users for the sweet talk compliment mode may include: users who have a romantic relationship with the current user, etc., who can convert the mediocre first content into, for example, sweet compliment content. It can be understood that the beautiful speech mode in the embodiment of the present invention can be used to improve the language quality of the first content, and there is no limitation on the specific beautiful speech mode.
[0085] In practical applications, the target flattery mode corresponding to the first content may be determined based on at least one pre-set flattery mode, that is, the flattery mode corresponding to the first content may be selected from at least one pre-set flattery mode as the target flattery mode.
[0086] The embodiment of the present invention may provide the following determination method for determining the target compliment mode corresponding to the first content:
[0087] Determination method 1: in response to a trigger instruction of the current user, taking the flattering mode corresponding to the trigger instruction as the target flattering mode corresponding to the first content; or
[0088] Determination method 2: determining a target compliment pattern corresponding to the first content according to a social relationship between the current user and a peer user corresponding to the first content and / or a historical compliment pattern used.
[0089] Determination method 1 may use the compliment mode corresponding to the trigger instruction of the current user as the target compliment mode corresponding to the first content. In actual application, a UI (User Interface) or a physical button may be provided to the current user so that the current user generates the above trigger instruction through the UI or the physical button.
[0090] For example, the UI provided to the current user may include: at least one kind of flattery mode, and the current user generates the above-mentioned trigger instruction for one of the flattery modes. Then, this embodiment of the present invention can use the flattery mode corresponding to the trigger instruction as the target flattery mode corresponding to the first content.
[0091] For another example, the physical button provided to the current user may be a physical button included in the smart terminal, so that the user can trigger the above trigger instruction by means of a shortcut key. The physical button may be a physical button already existing in the smart terminal, such as a key or key combination in a physical keyboard, a combination of a volume key and a power key, etc.
[0092] In order to improve the convenience of user operation and avoid conflicts between the shortcut keys corresponding to the trigger instructions and the existing shortcut keys, an optional embodiment of the present invention can set a touch device on the back or side of the smart terminal so that the user can generate the above touch instructions through the touch device. The touch device can be located on the shell of the smart terminal, or on the film on the back or side, so that the user can easily generate the above trigger instructions. The shell can be a replaceable shell of a smart terminal component provided by the manufacturer of the smart terminal, or a protective shell for protecting the smart terminal.
[0093] In actual applications, the user's trigger signal can be detected by the physical button or UI of the mobile terminal, and the physical button or UI can be used as the resource spent by the mobile terminal to detect the trigger signal. However, for physical buttons such as volume buttons and power buttons, the corresponding shortcut key functions are pre-set. Therefore, if the physical button is used to implement the newly added trigger signal, it is easy to cause a conflict in the shortcut key function. For example, when the UI is used to detect the user's trigger signal, it is necessary to set a corresponding detection area in the UI. The detection area will be a redundant area relative to the relatively fixed UI, so the corresponding design cost will be increased. For example, the input interface of the input method program is relatively fixed, which can usually include a syllable area, a candidate area and a keyboard area. If the detection area corresponding to the trigger signal is set in the input interface, the design cost of the input interface will increase. The embodiment of the present invention can effectively solve the conflict problem of shortcut key functions, and can realize the detection of trigger signals without changing the UI.
[0094] In one embodiment of the present invention, the touch control device may provide a rotary button so that the user can switch between the speech modes through the rotary button. Of course, the rotary button is only used as an example. In fact, the user can also switch between the speech modes through the non-rotating button. For example, the non-rotating button can be a single button, and a trigger instruction for the non-rotating button can be used as a switching instruction for the speech mode; or, the non-rotating button can be an up and down button, and the trigger instruction for the upper button can be used as an instruction for switching up, and the trigger instruction for the lower button can be used as an instruction for switching down. For example, the embodiment of the present invention can provide M (M is a positive integer) preset speech modes, and the user can switch between M preset speech modes through the rotary button. For example, if the current speech mode is numbered i, the trigger instruction for the upper button can switch from the speech mode numbered i to the speech mode numbered i-1, and the trigger instruction for the lower button can switch from the speech mode numbered i to the speech mode numbered i+1.
[0095] In another embodiment of the present invention, the touch control device may provide a touch control chip to sense a trigger instruction generated by a user through the touch control chip; it can be understood that the embodiment of the present invention does not limit the specific touch control device.
[0096] In order to improve the convenience of user operation, in another optional embodiment of the present invention, the trigger instruction is a voice instruction triggered by the current user, and the embodiment of the present invention can perform voice recognition on the voice instruction to obtain the compliment mode corresponding to the voice instruction. For example, if the voice instruction is "super manager", the embodiment of the present invention can obtain the compliment mode corresponding to the voice instruction as "super manager compliment mode" through voice recognition. The above trigger instruction is a voice instruction triggered by the current user, which can improve the convenience of the user generating the above trigger instruction.
[0097] Determination method 2 may automatically determine a target compliment pattern corresponding to the first content according to a social relationship between the current user and a peer user corresponding to the first content and / or a historical compliment pattern used.
[0098] Optionally, the above-mentioned determination method 2 adopted for determining the target compliment mode corresponding to the first content based on the social relationship between the current user and the opposite user corresponding to the first content and / or the historical compliment modes used may include:
[0099] Determining method 21: selecting, from the historical nicety patterns used between the current user and the opposite user corresponding to the first content, a historical nicety pattern with a usage frequency exceeding a frequency threshold as a target nicety pattern corresponding to the first content; and / or
[0100] Determining method 22: acquiring a target flattering pattern corresponding to the first content from preset flattering patterns according to a matching degree between a social relationship between the current user and a peer user corresponding to the first content and a flattering pattern; and / or
[0101] Determining method 23: determining a target compliment mode corresponding to the first content according to the compliment mode used by the current user's interest friends under the first content.
[0102] For determination method 21, the embodiment of the present invention can maintain the historical input behavior data of the current user, and the historical input behavior data can include: the historical compliment mode used by the current user during the input process and the corresponding peer user. For example, if the current user A uses the "super manager compliment mode" to send recommended content to the peer user B, the corresponding historical input behavior data can include: "super manager compliment mode" and user B. In practical applications, the historical input behavior data can be analyzed to obtain the usage frequency of a certain historical compliment mode used between the current user and the peer user corresponding to the first content. Among them, the usage frequency of a certain historical compliment mode can be: the ratio of the number of times the historical compliment mode used by the current user A and the peer user B is used to the number of times all historical compliment modes used by the current user A and the peer user B are used. When the usage frequency exceeds the frequency threshold, the corresponding historical compliment mode can be used as the target compliment mode corresponding to the first content. Since a reasonable target compliment mode and its corresponding compliment content can be provided to the current user, the user's selection cost for the compliment mode can be saved.
[0103] Regarding determination method 22, the embodiment of the present invention may obtain a target flattering pattern corresponding to the first content from preset flattering patterns based on the degree of match between the social relationship between the current user and the opposite user corresponding to the first content and the flattering pattern.
[0104] In the embodiment of the present invention, social relations can be the communication between people in society, which is the consciousness of people using certain methods (tools) to transmit information and exchange ideas to achieve certain social activities. Examples of social relations may include: customers, colleagues (leaders, subordinates), friends, lovers, competitors, etc.
[0105] In actual applications, the social relationship between the current user and the peer user corresponding to the first content can be determined based on the information of the peer user in the communication APP. For example, the social relationship between the current user and the peer user corresponding to the first content can be determined based on the notes or grouping information of the peer user in the address book or instant messaging application.
[0106] In an optional embodiment of the present invention, the social relationship between the current user and the opposite user corresponding to the first content can be determined based on the communication content between the opposite user and the user, and the corresponding determination process may include: obtaining the communication content between the opposite user and the user; extracting the first predetermined keyword contained in the communication content; and determining the social relationship between the opposite user and the user based on the first predetermined keyword.
[0107] For example, a database may be preset, which includes at least one social relationship and a keyword corresponding to each social relationship, as shown in Table 2:
[0108] Table 1
[0109]
[0110] After obtaining the communication content between the peer user and the current user, it can be determined whether the communication content contains any of the above keywords. If any of the above keywords are contained, they are extracted as first predetermined keywords, and then the social relationship between the peer user and the user is determined based on the first predetermined keywords. The corresponding determination process may include:
[0111] ① Determine the probability that the opposite user and the current user belong to each candidate social relationship respectively through the first predetermined keyword; determine the social relationship between the opposite user and the current user based on the probability.
[0112] For example, it is assumed that the first predetermined keyword includes the keywords shown in Table 3:
[0113] Table 2
[0114]
[0115] Then the number of occurrences of the keywords under each social relationship can be determined, and then based on the number of occurrences divided by the total number of occurrences, the probability that the peer user and the current user belong to the corresponding social relationship can be determined. For example: the number of occurrences of the keywords under the social relationship "couple" is 1001+355+201=1557, and the total number of occurrences of the keywords is 1557+50=1607, then it can be determined that the probability that the peer user and the current user belong to a couple social relationship is 1557 / 1607, and the probability of belonging to a husband and wife social relationship is 50 / 1607, and then the social relationship with the highest probability of occurrence is obtained as the social relationship between the peer user and the current user of the first data to be replied, for example: the couple social relationship is used as the social relationship between the peer user and the user, and so on. Based on this scheme, at least one keyword contained in each social relationship is considered, so the determined social relationship is more accurate.
[0116] ② Obtain the keyword with the highest number of occurrences from the first predetermined keywords; determine the social relationship corresponding to the keyword with the highest number of occurrences as the corresponding relationship between the peer user and the current user.
[0117] Taking the first predetermined keyword shown in Table 2 as an example, the keyword with the highest number of occurrences is "Smecta", and its corresponding social relationship is a couple social relationship. Therefore, it can be determined that the social relationship between the opposite user and the current user is a couple social relationship. Based on this scheme, there is no need to calculate the probability of each social probability, so the amount of processing operations can be reduced.
[0118] The determination method 22 may calculate the matching degree between the social relationship between the current user and the opposite user corresponding to the first content and the flattery mode, and obtain the target flattery mode corresponding to the first content from the preset flattery mode according to the matching degree. For example, a first mapping relationship between the social relationship, the flattery mode, and the matching degree may be established in advance, and then the matching degree between the social relationship between the current user and the opposite user corresponding to the first content and the flattery mode may be obtained by searching the first mapping relationship. Alternatively, the name of the social relationship and other information may be matched with the name of the flattery mode and other information to obtain the matching degree.
[0119] In actual applications, one or more compliment patterns with the highest matching degree may be used as the target compliment pattern corresponding to the first content. In one example, the target compliment pattern corresponding to the customer social relationship may be the "super manager compliment pattern", the target compliment pattern corresponding to the friend social relationship may be the "poetry life compliment pattern", and the target compliment pattern corresponding to the lover social relationship may be the "sweet talk compliment pattern".
[0120] Determination method 23 can determine the target compliment mode corresponding to the first content according to the compliment mode used by the interest friends of the current user under the first content. The interest friends can be friends with the same interests and hobbies as the current user. In the embodiment of the present invention, the compliment mode used by the interest friends of the current user under the first content can be used as the target compliment mode corresponding to the first content to improve the accuracy of the target compliment mode.
[0121] After determining the target compliment pattern corresponding to the first content by any one of the above-mentioned determination methods 21 to 23, the embodiment of the present invention can convert the first content into compliment content that conforms to the target compliment pattern. The corresponding conversion process may include: inputting the first content into a target compliment model corresponding to the target compliment pattern; and using the compliment content output by the target compliment model as the compliment content corresponding to the first content.
[0122] In practical applications, a flattery model corresponding to a flattery mode can be pre-established, and the flattery model can be used to convert a content into a flattery content that conforms to the flattery mode. Optionally, the flattery model can be trained based on the first training data. The first training data may include: ordinary content samples before language beautification processing, and flattery content samples after language beautification processing of the ordinary content samples according to the flattery mode, wherein the first training data can be obtained from the Internet, or the first training data can be obtained manually. Among them, the flattery model can have the ability to convert from the first content to the flattery content through learning from the first training data, and optionally, the flattery model can be a language model, a machine learning model, etc. For example, the language model can be an N-gram language model or a neural network language model, etc. It can be understood that the embodiment of the present invention does not limit the specific flattery model.
[0123] For the above-mentioned application example 1, the embodiment of the present invention can automatically obtain the target compliment mode "super manager compliment mode" corresponding to the first content "Received, thank you", and input the first content into the compliment model corresponding to the "super manager compliment mode", and the compliment model corresponding to the "super manager compliment mode" outputs the compliment content corresponding to the first content, such as "Dear customer, you have a really great vision". In this way, the quality of the communication content transmitted to the opposite user can be improved.
[0124] In an application example 2 of the present invention, it is assumed that the first content is the reply content of the second content, and it is assumed that the second content and the first content are respectively "What do you think of a certain emergency in Europe" and "What does it have to do with me?". In this case, the tone corresponding to the first content "What does it have to do with me" is relatively stiff; and the embodiment of the present invention can automatically obtain the target compliment mode "Poetry Life Compliment Mode" corresponding to "What does it have to do with me?", and input the first content into the compliment model corresponding to the "Poetry Life Compliment Mode", and the compliment model corresponding to the "Poetry Life Compliment Mode" outputs the compliment content corresponding to the first content, such as "Life and death, a cold glance. Traveler, hurry on your way", in this way, the quality of the communication content transmitted to the opposite user can be improved.
[0125] It can be understood that the above-mentioned method of obtaining the compliment content through the target compliment model corresponding to the target compliment mode is only an optional embodiment of the conversion process of the embodiment of the present invention. In fact, the embodiment of the present invention can also adopt other conversion processes, for example, manually converting the first content into compliment content that conforms to the target compliment mode, and for another example, enriching the first content according to the target compliment mode to obtain richer compliment content, etc., wherein the context of the first content (such as the content sent by the opposite user, etc.) can also be considered in the process of converting the first content into compliment content that conforms to the target compliment mode. It can be understood that the embodiment of the present invention does not limit the specific process of converting the first content into compliment content that conforms to the target compliment mode.
[0126] The embodiment of the present invention can output compliment reply content corresponding to the second content to the current user, and the compliment reply content corresponding to the second content can be used to represent the reply content corresponding to the second content that has been beautified in the second language, and / or the reply content corresponding to the second content that meets the second preset compliment condition; because the above-mentioned second language beautification processing can improve the language quality of the reply content corresponding to the second content, and / or the above-mentioned second preset compliment condition can constrain the language quality of the reply content corresponding to the second content, therefore, the embodiment of the present invention can provide the user with compliment reply content without relying on the input of the current user, can improve the current user's reply efficiency to the second content, and can improve the quality of the communication content transmitted to the opposite user, thereby improving the quality of communication exchanges.
[0127] In the case where the communication content of the current user includes the second content, the embodiment of the present invention can automatically obtain the compliment reply content corresponding to the second content, and the compliment reply content corresponding to the second content can be used to represent the reply content corresponding to the second content that has been beautified in the second language, and / or the reply content corresponding to the second content that meets the second preset compliment condition; because the above-mentioned second language beautification processing can improve the language quality of the reply content corresponding to the second content, and / or the above-mentioned second preset compliment condition can constrain the language quality of the reply content corresponding to the second content, therefore, the embodiment of the present invention can provide the user with compliment reply content without relying on the input of the current user, can improve the current user's reply efficiency to the second content, and can improve the quality of the communication content transmitted to the opposite user.
[0128] In an optional embodiment of the present invention, the process of obtaining the recommended content corresponding to the communication content may include: identifying the intention of the peer user for the second content, and using the obtained intention identification information as the recommended content corresponding to the second content. Since the above intention identification information can reflect the true thoughts of the peer user for the second content, the above intention identification information can be provided to the current user, so that the current user can refer to the intention identification information to reply to the second content.
[0129] Optionally, the process of identifying the intention of the peer user for the second content may include: identifying the intention of the peer user for the second content based on historical input behavior data and / or psychological knowledge of at least one user in the entire network to obtain corresponding intention identification information. The entire network may refer to the entire Internet, that is, the Internet corresponding to all applications or websites, or the Internet corresponding to a certain application or website. For example, for an input method APP, the entire network may refer to the Internet involved in the input method APP.
[0130] The embodiment of the present invention can maintain the historical input behavior data of at least one user in the entire network. The historical input behavior data may include: the conversation content between the users at both ends (including the content to be replied and the reply content). By analyzing the conversation content between the users at both ends, the accurate intention corresponding to a certain content to be replied can be obtained. Therefore, the historical input behavior data of at least one user in the entire network can be used as the basis for identifying intention recognition information.
[0131] Psychology is a science that studies human psychological phenomena, mental functions and behaviors. It is both a theoretical discipline and an applied discipline. Psychological knowledge can be used to describe, explain, predict and influence behavior. Therefore, the embodiment of the present invention can identify the intention identification information of the peer user for the second content based on psychological knowledge.
[0132] In practical applications, historical input behavior data and psychological knowledge can also be used in combination to identify the intention of the peer user for the second content. For example, psychological knowledge can be used to analyze the conversation content between the two end users to obtain the accurate intention corresponding to a certain content to be replied, and the content to be replied between the two end users is used as the second training data of the intention model, and the intention model is trained based on the first training data. That is, the intention model can use the content to be replied between the two end users and the intention obtained based on psychological knowledge as the second training data, and use psychological knowledge to train the second training data to obtain the intention model. Then the second content can be input into the intention model, and the intention model outputs the intention of the peer user for the second content.
[0133] In an optional embodiment of the present invention, the obtaining of the recommended content corresponding to the communication content may include: identifying the intention of the peer user for the second content; and obtaining, based on the obtained intention identification information, the kind words reply content corresponding to the second content as the recommended content corresponding to the second content. The kind words reply content obtained based on the intention identification information can accurately respond to the above intention identification information and can improve the quality of the kind words reply content.
[0134] In an optional embodiment of the present invention, the process of obtaining the compliment reply content corresponding to the second content according to the intention recognition information may include: using the compliment reply rule corresponding to the intention recognition information, and obtaining the compliment reply content corresponding to the second content according to the intention recognition information. In actual applications, a second mapping relationship between the intention recognition information and the compliment reply rule may be established in advance, and the compliment reply content corresponding to the second content may be obtained by querying the second mapping relationship.
[0135] In an application example 3 of the present invention, assuming that the second content is "Let's break up", and the opposite user corresponding to the second content is the girlfriend of the current user, then the embodiment of the present invention can identify the intention recognition information of the girlfriend of the current user for the second content as: "I don't want to break up, just coax me", and obtain the reply rules corresponding to the intention recognition information (such as "rules for coaxing girlfriend", "rules for being loyal to girlfriend", etc.), and obtain the flattering reply content corresponding to the second content, for example, "If I don't hold your hand, I think it will be a lifelong mistake", thereby providing the quality of the flattering reply content.
[0136] In other application examples, the intent recognition information may also include: "Praise the customer", "Make the goddess happy", "Good night and goodbye", etc., and the embodiment of the present invention may preset corresponding kind words reply rules for each intent recognition information. For example, assuming that the second content is "Go to bed early", and the opposite user corresponding to the second content is the girlfriend of the current user, the corresponding intent recognition information and kind words reply rule may both be "Good night and goodbye", and the corresponding kind words reply content may be "Good night" or "Peace", etc.
[0137] It can be understood that the above process of obtaining the compliment reply content corresponding to the second content by using the compliment reply rules corresponding to the intention recognition information is only an optional embodiment. In fact, those skilled in the art can also adopt other acquisition processes for obtaining the compliment reply content corresponding to the second content according to actual application requirements. For example, the embodiment of the present invention can also obtain the reply content by using the reply rules corresponding to the intention recognition information, and then perform second language beautification processing on the reply content to obtain the corresponding compliment reply content; for another example, the embodiment of the present invention can also obtain the reply information without using the intention recognition information. It can be understood that the specific process of obtaining the compliment reply content corresponding to the second content according to the intention recognition information is not limited in the embodiment of the present invention.
[0138] In actual application, step 203 may output the recommended content obtained in step 202 to the current user for selection by the user. The recommended content obtained in step 202 may be one or more items.
[0139] For example, in the application environment of an input method APP, after the current user inputs the first content, the embodiment of the present invention can automatically replace the first content with the compliment content corresponding to the compliment mode selected by the current user based on the compliment mode selected by the current user; or, it can automatically obtain the target compliment mode corresponding to the first content and the compliment content that conforms to the target compliment mode, and display the compliment content in the form of candidate items. If the current user triggers a certain compliment content to be displayed, the first content can be replaced with the compliment content triggered by the current user.
[0140] For another example, in the application environment of an input method APP, after the current user receives the second content sent by the opposite user, the embodiment of the present invention can automatically obtain the intention recognition information corresponding to the second content, and display the intention recognition information in the form of a candidate item, so as to provide the above intention recognition information to the current user, so that the current user can refer to the intention recognition information to reply to the second content. Furthermore, in the process of the current user replying to the second content (for example, the current user calls up the input method program and inputs the second content in the communication window of the opposite user), the embodiment of the present invention can also automatically obtain the compliment reply content corresponding to the second content based on the intention recognition information, and display it. If the current user triggers a certain compliment reply content to be displayed, the compliment reply content triggered by the current user can be displayed on the screen.
[0141] It should be noted that the target compliment pattern of the embodiment of the present invention may be one or more, and the recommended content obtained based on a target compliment pattern in the embodiment of the present invention may be one or more. In practical applications, the recommended content corresponding to a target compliment pattern may be sorted according to certain sorting rules. For example, the sorting rule may be the language model score of the recommended content, the frequency of occurrence of the recommended content in the entire network, etc. It can be understood that the embodiment of the present invention does not limit the specific sorting rules.
[0142] Similarly, the embodiments of the present invention can also be applied to application environments other than input method APPs. For example, in the application environment of instant messaging APPs, after the current user inputs the first content, the embodiments of the present invention can also automatically replace the first content with the compliment content corresponding to the compliment mode selected by the current user based on the compliment mode selected by the current user; or, the compliment content corresponding to the first content can be automatically displayed. If the current user triggers a certain compliment content to be displayed, the first content can be replaced with the compliment content triggered by the current user. Or, after the current user receives the second content sent by the opposite user, the embodiments of the present invention can automatically display the compliment reply content. If the current user triggers a certain compliment reply content to be displayed, the compliment reply content triggered by the current user can be displayed on the screen.
[0143] In an optional embodiment of the present invention, when multiple recommended contents are obtained, the multiple recommended contents can be sorted and outputted according to the matching degree between the social relationship between the current user and the opposite user corresponding to the first content and the compliment patterns corresponding to the recommended contents. Among them, the recommended contents corresponding to compliment patterns with high matching degree can be ranked ahead of the recommended contents corresponding to compliment patterns with low matching degree. Since in the above scheme, the multiple recommended contents can be sorted differently according to the social relationship between the opposite user and the current user, the technical effect of more accurate recommendation of the multiple recommended contents is achieved.
[0144] In summary, the recommendation method of the embodiment of the present invention can output the compliment content corresponding to the first content to the current user. The compliment content corresponding to the first content can be the content corresponding to the first content that has been beautified in the first language, and / or the content corresponding to the first content that meets the first preset compliment condition. Since the above-mentioned first language beautification processing can improve the language quality of the first content, and / or the above-mentioned first preset compliment condition can constrain the language quality of the compliment content, the quality of the compliment content of the embodiment of the present invention can be higher than that of the first content. Therefore, the embodiment of the present invention can improve the quality of the communication content transmitted to the opposite user, and thus can improve the quality of communication exchanges.
[0145] Furthermore, the embodiment of the present invention can output complimenting reply content corresponding to the second content to the current user, and the complimenting reply content corresponding to the second content can be used to represent the reply content corresponding to the second content that has been beautified in the second language, and / or the reply content corresponding to the second content that meets the second preset complimenting condition; since the above-mentioned second language beautification processing can improve the language quality of the reply content corresponding to the second content, and / or the above-mentioned second preset complimenting condition can constrain the language quality of the reply content corresponding to the second content, therefore, the embodiment of the present invention can provide the user with complimenting reply content without relying on the input of the current user, can improve the current user's reply efficiency to the second content, and can improve the quality of the communication content transmitted to the opposite user, thereby improving the quality of communication exchanges.
[0146] It should be noted that, for the method embodiments, for the sake of simplicity of description, they are all described as a series of motion action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the described motion actions, 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 know that the embodiments described in the specification are all preferred embodiments, and the motion actions involved are not necessarily required by the embodiments of the present invention.
[0147] Device Embodiment
[0148] Reference Figure 3 , shows a structural block diagram of an embodiment of a recommendation device of the present invention, which may specifically include:
[0149] The communication content acquisition module 301 is used to acquire the communication content of the current user; the communication content of the current user may include: the first content input by the current user, and / or the second content received;
[0150] The recommended content acquisition module 302 is used to acquire the recommended content corresponding to the communication content; the recommended content may include: the compliment content corresponding to the first content, and / or the intention recognition information and / or the compliment reply content corresponding to the second content; and
[0151] The recommended content output module 303 is used to output the recommended content to the current user.
[0152] Optionally, the recommended content acquisition module 302 may include:
[0153] A mode determination submodule, used to determine a target compliment mode corresponding to the first content;
[0154] The conversion submodule is used to convert the first content into compliment content that conforms to the target compliment mode as the compliment content corresponding to the first content.
[0155] Optionally, the mode determination submodule may include:
[0156] A first determining unit is configured to, in response to a trigger instruction of the current user, use a flattering mode corresponding to the trigger instruction as a target flattering mode corresponding to the first content; or
[0157] a second determining unit, configured to determine a target compliment pattern corresponding to the first content according to a social relationship between the current user and a peer user corresponding to the first content and / or a historical compliment pattern used; or
[0158] The third determining unit is configured to determine a target compliment mode corresponding to the first content according to the compliment mode used by the current user's interest friends under the first content.
[0159] Optionally, the second determining unit may include:
[0160] a first selection subunit, configured to select, from the historical nicety patterns used between the current user and the opposite user corresponding to the first content, a historical nicety pattern with a usage frequency exceeding a frequency threshold as a target nicety pattern corresponding to the first content; and / or
[0161] The second selection subunit acquires a target sweetness pattern corresponding to the first content from preset sweetness patterns according to a matching degree between a social relationship between the current user and a counterpart user corresponding to the first content and the sweetness pattern.
[0162] Optionally, the trigger instruction may be an instruction triggered by the current user through a touch device located on the back or side of the smart terminal; or
[0163] The trigger instruction may be a voice instruction triggered by the current user.
[0164] Optionally, the conversion submodule may include:
[0165] A model input unit, configured to input the first content into a target flattery model corresponding to the target flattery model;
[0166] The model output unit is used to use the flattering content output by the target flattering model as the flattering content corresponding to the first content.
[0167] Optionally, the recommended content acquisition module 303 may include:
[0168] The intention identification submodule is used to identify the intention of the opposite user for the second content, and use the obtained intention identification information as the recommended content corresponding to the second content.
[0169] Optionally, the recommended content acquisition module 303 may further include:
[0170] The compliment reply content acquisition submodule is used to acquire the compliment reply content corresponding to the second content according to the intention recognition information as the recommended content corresponding to the second content.
[0171] Optionally, the intention recognition submodule may include:
[0172] The identification unit is used to identify the intention of the opposite user for the second content based on the historical input behavior data and / or psychological knowledge of at least one user in the entire network, so as to obtain corresponding intention identification information.
[0173] Optionally, the submodule for acquiring the content of the nice reply may include:
[0174] The reply rule acquisition unit is used to use the nice reply rule corresponding to the intention recognition information to acquire the nice reply content corresponding to the second content according to the intention recognition information.
[0175] 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.
[0176] 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.
[0177] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0178] Figure 4 1 is a block diagram of a device for recommendation as a terminal according to an exemplary embodiment. For example, the terminal 900 may be the aforementioned intelligent terminal, or a mobile terminal. For example, examples of terminals may include: mobile phones, computers, digital broadcast terminals, messaging devices, game consoles, tablet devices, medical devices, fitness equipment, personal digital assistants, etc.
[0179] Reference Figure 4 The terminal 900 may include one or more of the following components: a processing component 902 , a memory 904 , a power component 906 , a multimedia component 908 , an audio component 910 , an input / output (I / O) interface 912 , a sensor component 914 , and a communication component 916 .
[0180] The processing component 902 generally controls the overall operation of the terminal 900, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 902 may include one or more processors 920 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 902 may include one or more modules to facilitate the interaction between the processing component 902 and other components. For example, the processing component 902 may include a multimedia module to facilitate the interaction between the multimedia component 908 and the processing component 902.
[0181] The memory 904 is configured to store various types of data to support operations at the terminal 900. Examples of such data include instructions for any application or method operating on the terminal 900, contact data, phone book data, messages, pictures, videos, etc. The memory 904 may 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.
[0182] The power component 906 provides power to various components of the terminal 900. The power component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the terminal 900.
[0183] The multimedia component 908 includes a screen that provides an output interface between the terminal 900 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 motion action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 908 includes a front camera and / or a rear camera. When the terminal 900 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.
[0184] The audio component 910 is configured to output and / or input audio signals. For example, the audio component 910 includes a microphone (MIC), and when the terminal 900 is in an operation 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 904 or sent via the communication component 916. In some embodiments, the audio component 910 also includes a speaker for outputting audio signals.
[0185] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.
[0186] The sensor assembly 914 includes one or more sensors for providing various aspects of status assessment for the terminal 900. For example, the sensor assembly 914 can detect the open / closed state of the terminal 900, the relative positioning of the components, such as the display and keypad of the terminal 900, and the sensor assembly 914 can also detect the position change of the terminal 900 or a component of the terminal 900, the presence or absence of contact between the user and the terminal 900, the orientation or acceleration / deceleration of the terminal 900, and the temperature change of the terminal 900. The sensor assembly 914 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 914 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 914 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
[0187] The communication component 916 is configured to facilitate wired or wireless communication between the terminal 900 and other devices. The terminal 900 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 916 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 916 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.
[0188] In an exemplary embodiment, the terminal 900 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.
[0189] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 904 including instructions, and the instructions can be executed by a processor 920 of the terminal 900 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.
[0190] Figure 5 1 is a block diagram of a device for recommendation as a server according to an exemplary embodiment. The server 1900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 may be temporary storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server. Furthermore, the central processor 1922 may be configured to communicate with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.
[0191] The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1958, one or more keyboards 1956, and / or, one or more operating systems 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
[0192] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1932 including instructions, and the instructions can be executed by a processor of the server 1900 to complete 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.
[0193] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (such as a terminal or a server), the device is able to execute a recommendation method, the method comprising: obtaining the communication content of the current user; the communication content of the current user comprises: a first content input by the current user, and / or a second content received; obtaining recommended content corresponding to the communication content; the recommended content comprises: compliment content corresponding to the first content, and / or intention recognition information and / or compliment reply content corresponding to the second content; and outputting the recommended content to the current user.
[0194] Optionally, the acquiring recommended content corresponding to the communication content includes: determining a target complimenting pattern corresponding to the first content; and converting the first content into complimenting content conforming to the target complimenting pattern as the complimenting content corresponding to the first content.
[0195] Optionally, determining the target compliment pattern corresponding to the first content includes: responding to a trigger instruction of the current user, using the compliment pattern corresponding to the trigger instruction as the target compliment pattern corresponding to the first content; or determining the target compliment pattern corresponding to the first content based on a social relationship between the current user and a counterpart user corresponding to the first content and / or a historical compliment pattern used; or determining the target compliment pattern corresponding to the first content based on a compliment pattern used by the current user's interest friends under the first content.
[0196] Optionally, determining a target compliment pattern corresponding to the first content based on the social relationship between the current user and the opposite user corresponding to the first content and / or a historical compliment pattern used includes: selecting a historical compliment pattern whose usage frequency exceeds a frequency threshold from the historical compliment patterns used between the current user and the opposite user corresponding to the first content as the target compliment pattern corresponding to the first content; and / or obtaining the target compliment pattern corresponding to the first content from preset compliment patterns based on a matching degree between the social relationship between the current user and the opposite user corresponding to the first content and the compliment pattern.
[0197] Optionally, the trigger instruction is an instruction triggered by the current user through a touch device located on the back or side of the smart terminal; or the trigger instruction is a voice instruction triggered by the current user.
[0198] Optionally, converting the first content into compliment content that conforms to the target compliment mode includes: inputting the first content into a target compliment model corresponding to the target compliment mode; and using the compliment content output by the target compliment model as the compliment content corresponding to the first content.
[0199] Optionally, the acquiring recommended content corresponding to the communication content includes: identifying an intention of a peer user for the second content, and using the obtained intention identification information as the recommended content corresponding to the second content.
[0200] Optionally, the obtaining recommended content corresponding to the communication content further includes: obtaining, based on the intention recognition information, a compliment reply content corresponding to the second content as the recommended content corresponding to the second content.
[0201] Optionally, the identifying of the intention recognition information of the peer user with respect to the second content includes: based on historical input behavior data and / or psychological knowledge of at least one user in the entire network, identifying the intention of the peer user with respect to the second content to obtain corresponding intention recognition information.
[0202] Optionally, obtaining the compliment reply content corresponding to the second content based on the intention identification information includes: utilizing the compliment reply rule corresponding to the intention identification information, and obtaining the compliment reply content corresponding to the second content based on the intention identification information.
[0203] The protective device provided by the embodiment of the present invention may include: a first surface that fits with the mobile terminal; a touch component is provided on the portion of the protective device other than the first surface, and the touch component can be used to detect a trigger signal generated by a user. Through the protective device of the embodiment of the present invention, the user can generate a trigger signal through the touch component, thereby improving the convenience of the user generating a trigger signal.
[0204] Moreover, since the protection device can be independent of the mobile terminal, the embodiment of the present invention can reduce the resources spent by the mobile terminal to detect the trigger signal to a certain extent. For example, in practical applications, the user's trigger signal can be detected by the physical button or UI (User Interface) of the mobile terminal, and the physical button or UI can be used as the resources spent by the mobile terminal to detect the trigger signal. However, for physical buttons such as volume buttons and power buttons, corresponding shortcut key functions are pre-set. Therefore, if the physical button is used to implement the newly added trigger signal, it is easy to cause a conflict of shortcut key functions. For another example, when the UI is used to detect the user's trigger signal, it is necessary to set a corresponding detection area in the UI. The detection area will be a redundant area relative to the relatively fixed UI, so the corresponding design cost will be increased. For example, the input interface of the input method program is relatively fixed, which can usually include a syllable area, a candidate area and a keyboard area. If the detection area corresponding to the trigger signal is set in the input interface, the design cost of the input interface will be increased. The embodiment of the present invention can effectively solve the conflict problem of shortcut key functions, and can realize the detection of trigger signals without changing the UI.
[0205] In practical applications, the protective device may be a protective film, protective cover, or other device that protects the mobile terminal. The protective device may be mounted on the mobile terminal through the first surface. For example, the first surface may be mounted on the rear shell of the mobile terminal to achieve adhesion between the protective device and the rear shell.
[0206] In one embodiment of the present invention, the touch component may be a touch sensing chip. For example, a touch sensing chip may be provided on a second surface opposite to the first surface, and the user's trigger signal may be sensed by the touch sensing chip. For example, the trigger signal may be a trigger signal corresponding to a touch mode such as single click, double click, or sliding, wherein the touch sensing chip may also detect the pressing force of the trigger signal to distinguish different trigger signals by different pressing forces. Optionally, the touch sensing chip may use capacitive touch sensing technology or resistive touch sensing technology to detect and sense the user's trigger signal. It is to be understood that the embodiment of the present invention does not limit the specific touch sensing technology used by the touch sensing chip.
[0207] In another embodiment of the present invention, the touch component may be a touch button. For example, the touch button may be a rotating button, so that the user can switch between mode contents through the rotating button. Of course, the rotating button is only used as an example. In fact, the user can also switch between mode contents through a non-rotating button. For example, the non-rotating button may be a single button, and a trigger instruction for the non-rotating button may be used as a switching instruction for mode contents, etc.; or, the non-rotating button may be an up-down button, and the trigger instruction for the upper button may be used as an instruction for switching up, and the trigger instruction for the lower button may be used as an instruction for switching down. For example, an embodiment of the present invention may provide M (M is a positive integer) preset mode contents, and the user may switch between M preset mode contents through the rotating button. For example, if the current mode content is numbered i, the trigger instruction for the upper button may switch from the mode content numbered i to the mode content numbered i-1, and the trigger instruction for the lower button may switch from the mode content numbered i to the mode content numbered i+1. It can be understood that the switching between the above-mentioned mode contents is only an example of the application scenario of the trigger signal of the present invention. In fact, the embodiment of the present invention does not limit the specific application scenario of the trigger signal.
[0208] In an optional embodiment of the present invention, the touch component may be located on the second surface and / or the side surface, wherein the second surface is arranged opposite to the first surface, and the side surface may be a surface adjacent to the first surface and the second surface respectively. Assuming that the first surface is in contact with the rear shell of the mobile terminal, when the user uses the front screen of the mobile terminal, the corresponding trigger signal can be conveniently generated by the touch component located on the back or side surface.
[0209] In an optional embodiment of the present invention, the protection device may further include: a signal transmitter, the signal transmitter is used to transmit the trigger signal to the mobile terminal, so that the mobile terminal responds to the trigger signal. For example, in an application scenario applied to switching between mode contents, the mobile terminal can switch the mode content according to the trigger signal.
[0210] Optionally, the signal transmitter may include: an NFC (Near Field Communication) chip. NFC is a contactless identification interconnection technology that can perform short-range wireless communication between different devices. It can be understood that the above-mentioned NFC chip is only an optional embodiment of the signal transmitter. In fact, the signal transmitter of the present invention can also transmit trigger signals based on infrared, Bluetooth and other communication technologies. The embodiments of the present invention do not limit the specific signal transmitter.
[0211] In an optional embodiment of the present invention, the protection device further includes: a memory, which can be used to store mode content to determine the target mode content corresponding to the trigger signal. The above-mentioned mode content can be the mode content of the operating system or application of the mobile terminal for user selection, wherein those skilled in the art can determine the above-mentioned mode content according to actual application requirements, for example, the above-mentioned mode content can be the beautiful words mode content, or the desktop wallpaper content, etc. It can be understood that the present invention does not limit the specific mode content.
[0212] The desktop wallpaper content can be used to represent the desktop background of the mobile terminal. The desktop background can be switched through the touch control component of the embodiment of the present invention.
[0213] A protection device provided by the present invention is described in detail below through a specific embodiment. For the sake of convenience, a mobile phone will be used as a specific example of the mobile terminal of the present invention. Those skilled in the art can understand that in addition to mobile phones as mobile terminals, it can also be applied to other mobile terminals, such as tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, wearable devices, etc. are all within the protection scope of the embodiments of the present invention.
[0214] Reference Figure 6 and Figure 7 , respectively showing a schematic diagram of the structure of a protective device 1 and a mobile terminal 2 in a state of being attached to each other according to an embodiment of the present invention, referring to Figure 8 , showing a schematic structural diagram of a protection device 1 according to an embodiment of the present invention; wherein the protection device 1 may include a first surface 3, and the protection device 1 may be mounted on the rear shell of the mobile terminal 2 by attaching the first surface 3 to the mobile terminal 2.
[0215] In practical applications, the protective device 1 may be provided with a touch component on a portion other than the first surface 3. For example, Figures 6 to 8 In the embodiment, a touch sensing chip (not shown in the figure) can be set inside the second surface opposite to the first surface 3, and the user's trigger signal can be sensed by the touch sensing chip. For example, the trigger signal can be a trigger signal corresponding to a single click, a double click, or a slide.
[0216] In other embodiments of the present invention, the protection device 1 may be provided with a touch button on a portion other than the first surface 3 , so that the user can sense the user's trigger signal through the touch button.
[0217] In one embodiment of the present invention, the protection device 1 may include a signal transmitter (not shown in the figure), which may transmit the trigger signal to the mobile terminal so that the mobile terminal responds to the trigger signal. For example, in an application scenario where switching between mode contents is applied, the mobile terminal may switch the mode content according to the trigger signal.
[0218] It should be noted that the trigger signals generated by different touch modes can be used to switch between different mode contents. For example, for the first touch mode such as single click, the mode content used for switching can be a beautiful speech mode or a theme of a desktop wallpaper; for the second touch mode such as double click or slide, the mode content used for switching can be switching between different recommended contents corresponding to the same beautiful speech mode, or switching between different desktop wallpapers corresponding to the theme of the desktop wallpaper. Alternatively, the first touch mode can also be a single click of a first pressing force, and the second touch mode can be a single click of a second pressing force.
[0219] The shell provided by the embodiment of the present invention may include: the shell is hollow inside to form a receiving cavity, and the shell side wall may be provided with an opening for allowing the mobile terminal body to extend into the receiving cavity; and the shell may be provided with a touch component outside, and the touch component is used to detect a trigger signal generated by a user. Through the shell of the embodiment of the present invention, the user can generate a trigger signal through the touch component, thereby improving the convenience of the user generating a trigger signal.
[0220] Moreover, since the shell can be independent of the mobile terminal, the embodiment of the present invention can reduce the resources spent by the mobile terminal to detect the trigger signal to a certain extent. For example, the embodiment of the present invention can effectively solve the conflict problem of shortcut key functions and can realize the detection of trigger signals without changing the UI.
[0221] In practical applications, the shell may be a front shell, a rear shell, etc. of a mobile terminal, and the shell may be assembled with the mobile terminal through the accommodating cavity.
[0222] In one embodiment of the present invention, the touch component may be a touch sensing chip. In another embodiment of the present invention, the touch component may be a touch button. For example, the touch button may be a rotation button or a non-rotation button, and the number of the touch buttons may be one or more, wherein different trigger signals may be detected by different touch buttons.
[0223] In an optional embodiment of the present invention, the touch component may be located on the back and / or side of the housing. Assuming that the housing is a rear housing of a mobile terminal, when the user uses the front screen of the mobile terminal, the corresponding trigger signal can be conveniently generated by the touch component located on the back or side.
[0224] In an optional embodiment of the present invention, the housing may further include: a signal transmitter, the signal transmitter being used to transmit the trigger signal to the mobile terminal so that the mobile terminal responds to the trigger signal. For example, in an application scenario where switching between mode contents is applied, the mobile terminal may switch the mode contents according to the trigger signal.
[0225] Optionally, the signal transmitter may include: an NFC chip.
[0226] In an optional embodiment of the present invention, the housing may further include: a memory, which may be used to store mode content to determine the target mode content corresponding to the trigger signal.
[0227] Reference Fig. 9 , showing a schematic diagram of a rear view of a rear shell 4 of an embodiment of the present invention; wherein, a touch sensing chip (not shown in the figure) may be provided on the outside (including the side or front) of the rear shell 4, and the user's trigger signal may be sensed by the touch sensing chip.
[0228] Reference Fig.10 , showing a schematic diagram of a rear view of a rear shell 4 of an embodiment of the present invention; wherein, a first touch button 5 can be provided on the front of the rear shell 4, and the user's trigger signal can be detected by the first touch button 5.
[0229] Reference Fig.11 , showing a schematic diagram of a rear view of a rear shell 4 of an embodiment of the present invention; wherein, a rotating button 6 can be provided on the front of the rear shell 4, and the user's trigger signal can be detected by the rotating button 6.
[0230] Reference Fig.12 , shows a schematic diagram of a rear view of a rear housing 4 of an embodiment of the present invention; wherein, a first upper button 7 and a first lower button 8 may be provided on the front of the rear housing 4, and a user's trigger signal may be detected by the upper button 7 and the lower button 8. The trigger instruction of the first upper button may be used as an instruction for switching upward, and the trigger instruction of the first lower button may be used as an instruction for switching downward.
[0231] Reference Fig.13, showing a schematic side view of a rear shell 4 of an embodiment of the present invention; wherein, a second touch button 9 may be provided on the left side or the right side of the rear shell 4, and the user's trigger signal may be detected by the second touch button 9.
[0232] Reference Fig.14 , showing a schematic side view of a rear shell 4 of an embodiment of the present invention; wherein, a second upper button 10 and a second lower button 11 may be provided on the left side or the right side of the rear shell 4, and the user's trigger signal may be detected by the second upper button 10 and the second lower button 11.
[0233] It is understandable that the above Fig.13 and Fig.14 The manner of arranging the touch buttons on the left side or the right side of the rear housing 4 is only taken as an example, and of course, the touch buttons can also be arranged on the upper side or the lower side.
[0234] In one embodiment of the present invention, the housing 4 may include a memory (not shown in the figure), which may be used to store mode content to determine the target mode content corresponding to the trigger signal. For example, the above-mentioned mode content may be a beautiful speech mode content. Assuming that the memory can store M kinds of beautiful speech mode content (numbered 1, 2, ...M), and assuming that the number of touch components is 1, then in the initial case, if a trigger signal is received through the touch component, the beautiful speech mode content numbered 1 may be used as the target mode content corresponding to the trigger signal, and the target mode content corresponding to the trigger signal is sent to the mobile terminal through the signal transmitter, so that the mobile terminal switches the beautiful speech mode content to the beautiful speech mode content numbered 1. In subsequent cases, if a trigger signal is received again, the beautiful speech mode content numbered 2 may be used as the target mode content corresponding to the trigger signal, and the target mode content corresponding to the trigger signal is sent to the mobile terminal, so that the mobile terminal switches the beautiful speech mode content to the beautiful speech mode content numbered 2. Further, after the mobile terminal switches the beautiful speech mode content to a certain target beautiful speech mode content, the mobile terminal may provide the user with at least one recommended content corresponding to the target beautiful speech mode content.
[0235] Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.
[0236] It should be understood that the present invention is not limited to the precise structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
[0237] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
[0238] The above is a detailed introduction to a recommendation method, a recommendation device, and a device for recommendation 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 a limitation on the present invention.
Claims
1. A recommendation method, characterized in that: include: Get the communication content of the current user; The communication content of the current user includes: the first content input by the current user and the second content received; Acquire recommended content corresponding to the communication content; the recommended content includes: compliment content corresponding to the first content, intention recognition information and compliment reply content corresponding to the second content; Outputting the recommended content to the current user; The obtaining of the recommended content corresponding to the communication content includes: determining a target complimenting pattern corresponding to the first content; converting the first content into complimenting content conforming to the target complimenting pattern as complimenting content corresponding to the first content; identifying the intention of the peer user for the second content, and using the obtained intention identification information as the recommended content corresponding to the second content, including: identifying the intention of the peer user for the second content based on historical input behavior data of at least one user in the entire network, so as to obtain corresponding intention identification information.
2. The method according to claim 1, characterized in that The determining a target compliment mode corresponding to the first content includes: In response to a trigger instruction of the current user, taking the flattering mode corresponding to the trigger instruction as a target flattering mode corresponding to the first content; or Determining a target compliment pattern corresponding to the first content according to a social relationship between the current user and a peer user corresponding to the first content and / or a historical compliment pattern used; or According to the compliment mode used by the current user's interest friends under the first content, a target compliment mode corresponding to the first content is determined.
3. The method according to claim 2, characterized in that The determining, based on the social relationship between the current user and the opposite user corresponding to the first content and / or the historical compliment patterns used, a target compliment pattern corresponding to the first content includes: Selecting, from the historical nicety patterns used between the current user and the opposite user corresponding to the first content, a historical nicety pattern with a usage frequency exceeding a frequency threshold as a target nicety pattern corresponding to the first content; and / or According to the matching degree between the social relationship between the current user and the opposite user corresponding to the first content and the flattery pattern, a target flattery pattern corresponding to the first content is acquired from preset flattery patterns.
4. The method according to claim 2, characterized in that: The trigger instruction is an instruction triggered by the current user through a touch device located on the back or side of the smart terminal; or The trigger instruction is a voice instruction triggered by the current user.
5. The method according to claim 1, characterized in that The converting the first content into a flattering content conforming to the target flattering mode includes: inputting the first content into a target beautiful speech model corresponding to the target beautiful speech mode; The flattering content output by the target flattering model is used as the flattering content corresponding to the first content.
6. The method according to claim 1, characterized in that The obtaining of recommended content corresponding to the communication content further includes: According to the intention recognition information, a compliment reply content corresponding to the second content is obtained as recommended content corresponding to the second content.
7. The method according to claim 1, characterized in that The identifying the intention identification information of the opposite user for the second content includes: Based on psychological knowledge, the intention of the opposite user with respect to the second content is identified to obtain corresponding intention identification information.
8. The method according to claim 6, characterized in that The acquiring, based on the intention identification information, the kind reply content corresponding to the second content includes: The compliment reply rule corresponding to the intention identification information is utilized, and based on the intention identification information, the compliment reply content corresponding to the second content is acquired.
9. A recommendation device, characterized in that: include: A communication content acquisition module, used to acquire the communication content of the current user; The communication content of the current user includes: the first content input by the current user and the second content received; a recommended content acquisition module, configured to acquire recommended content corresponding to the communication content; the recommended content includes: compliment content corresponding to the first content, intention recognition information and compliment reply content corresponding to the second content; and A recommended content output module, used to output the recommended content to the current user; The recommended content acquisition module includes: A mode determination submodule, used to determine a target compliment mode corresponding to the first content; A conversion submodule, configured to convert the first content into compliment content that conforms to the target compliment mode as the compliment content corresponding to the first content; The intention identification submodule is used to identify the intention of the peer user for the second content, and use the obtained intention identification information as the recommended content corresponding to the second content, including: based on the historical input behavior data of at least one user in the entire network, identifying the intention of the peer user for the second content to obtain corresponding intention identification information.
10. The device according to claim 9, characterized in that The mode determination submodule comprises: A first determining unit is configured to, in response to a trigger instruction of the current user, use a flattering mode corresponding to the trigger instruction as a target flattering mode corresponding to the first content; or a second determining unit, configured to determine a target compliment pattern corresponding to the first content according to a social relationship between the current user and a peer user corresponding to the first content and / or a historical compliment pattern used; or The third determining unit is configured to determine a target compliment mode corresponding to the first content according to the compliment mode used by the current user's interest friends under the first content.
11. The device according to claim 10, characterized in that The second determining unit includes: a first selection subunit, configured to select, from the historical nicety patterns used between the current user and the opposite user corresponding to the first content, a historical nicety pattern with a usage frequency exceeding a frequency threshold as a target nicety pattern corresponding to the first content; and / or The second selection subunit acquires a target sweetness pattern corresponding to the first content from preset sweetness patterns according to a matching degree between a social relationship between the current user and a counterpart user corresponding to the first content and the sweetness pattern.
12. The device according to claim 10, characterized in that The trigger instruction is an instruction triggered by the current user through a touch device located on the back or side of the smart terminal; or The trigger instruction is a voice instruction triggered by the current user.
13. The device according to claim 9, characterized in that The conversion submodule comprises: A model input unit, configured to input the first content into a target flattery model corresponding to the target flattery model; The model output unit is used to use the flattering content output by the target flattering model as the flattering content corresponding to the first content.
14. The device according to claim 9, characterized in that The recommended content acquisition module also includes: The compliment reply content acquisition submodule is used to acquire the compliment reply content corresponding to the second content according to the intention recognition information as the recommended content corresponding to the second content.
15. The device according to claim 9, characterized in that The intention recognition submodule includes: The identification unit is used to identify the intention of the opposite user for the second content based on psychological knowledge to obtain corresponding intention identification information.
16. The device according to claim 14, characterized in that The submodule for obtaining the content of the nice reply includes: The reply rule acquisition unit is used to use the kind reply rule corresponding to the intention recognition information to acquire the kind reply content corresponding to the second content according to the intention recognition information.
17. A device for recommendation, 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, and the one or more programs include instructions for performing the following operations: Get the communication content of the current user; The communication content of the current user includes: the first content input by the current user and the second content received; Acquire recommended content corresponding to the communication content; the recommended content includes: compliment content corresponding to the first content, intention recognition information and compliment reply content corresponding to the second content; Outputting the recommended content to the current user; The obtaining of recommended content corresponding to the communication content includes: Determine a target compliment mode corresponding to the first content; converting the first content into compliment content that conforms to the target compliment mode as the compliment content corresponding to the first content; Identify the intention of the peer user for the second content, and use the obtained intention identification information as the recommended content corresponding to the second content, including: based on the historical input behavior data of at least one user in the entire network, identify the intention of the peer user for the second content to obtain the corresponding intention identification information.
18. The device according to claim 17, characterized in that The determining a target compliment mode corresponding to the first content includes: In response to a trigger instruction of the current user, taking the flattering mode corresponding to the trigger instruction as a target flattering mode corresponding to the first content; or Determining a target compliment pattern corresponding to the first content according to a social relationship between the current user and a peer user corresponding to the first content and / or a historical compliment pattern used; or According to the compliment mode used by the current user's interest friends under the first content, a target compliment mode corresponding to the first content is determined.
19. The device according to claim 18, characterized in that The determining, based on the social relationship between the current user and the opposite user corresponding to the first content and / or the historical compliment patterns used, a target compliment pattern corresponding to the first content includes: Selecting, from the historical nicety patterns used between the current user and the opposite user corresponding to the first content, a historical nicety pattern with a usage frequency exceeding a frequency threshold as a target nicety pattern corresponding to the first content; and / or According to the matching degree between the social relationship between the current user and the opposite user corresponding to the first content and the flattery pattern, a target flattery pattern corresponding to the first content is acquired from preset flattery patterns.
20. The device according to claim 18, characterized in that The trigger instruction is an instruction triggered by the current user through a touch device located on the back or side of the smart terminal; or The trigger instruction is a voice instruction triggered by the current user.
21. The device according to claim 17, characterized in that The converting the first content into a flattering content conforming to the target flattering mode includes: inputting the first content into a target beautiful speech model corresponding to the target beautiful speech mode; The flattering content output by the target flattering model is used as the flattering content corresponding to the first content.
22. The device according to claim 17, characterized in that The obtaining of recommended content corresponding to the communication content further includes: According to the intention recognition information, a compliment reply content corresponding to the second content is obtained as recommended content corresponding to the second content.
23. The device according to claim 17, characterized in that The identifying the intention identification information of the opposite user for the second content includes: Based on psychological knowledge, the intention of the opposite user with respect to the second content is identified to obtain corresponding intention identification information.
24. The device according to claim 22, characterized in that The acquiring, based on the intention identification information, the kind reply content corresponding to the second content includes: The compliment reply rule corresponding to the intention identification information is utilized, and based on the intention identification information, the compliment reply content corresponding to the second content is acquired.
25. A machine-readable medium having stored thereon instructions which, when executed by one or more processors, cause an apparatus to perform the method of one or more of claims 1 to 8.
