Data processing method, device and equipment, computer readable storage medium and product

Abstract

The embodiment of the invention provides a data processing method and device, equipment, a computer readable storage medium and a product. The method comprises the steps that a session text is displayed in a session interface; displaying at least one expression item associated with the session text in a preset display area in the session interface, wherein the expression item is determined in a plurality of preset expressions based on the text length of the session text and at least one kind of preset expression associated data or current time information; and in response to a triggering operation on the expression item, sending a currently triggered first preset expression in the session interface. Therefore, for the session texts with different lengths, the expression items more fitting the session text association can be recommended to the user, and the accuracy of expression recommendation is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of data processing, and in particular, to a data processing method, device, equipment, computer readable storage medium and product. BACKGROUND

[0002] As a core tool of modern socialization and communication, the semantic expression function of instant messenger (IM) directly affects user stickiness and use experience. In daily use, users often convey complex semantics through the combination of text and emoticons (such as emoji or custom emoticons).

[0003] However, the emoticon recommendation function in the existing IM system can only handle short sentences or single semantic inputs, and cannot analyze the multi-layer context in long sentences, resulting in a disconnection between the recommended results and the actual needs of users, and low accuracy. SUMMARY

[0004] Embodiments of the present disclosure provide a data processing method, device, equipment, computer readable storage medium and product, to solve the technical problem that the emoticon recommendation function cannot analyze multi-layer semantics and context in long sentences, resulting in low accuracy of recommended results.

[0005] In a first aspect, embodiments of the present disclosure provide a data processing method, comprising:

[0006] displaying conversation text in a conversation interface;

[0007] displaying at least one emoticon item associated with the conversation text in a preset display area in the conversation interface, the emoticon item being determined based on the text length of the conversation text and at least one preset emoticon association data or current time information in a plurality of preset emoticons;

[0008] in response to a triggering operation on the emoticon item, sending a first preset emoticon currently triggered in the conversation interface.

[0009] In a second aspect, embodiments of the present disclosure provide a data processing method, comprising:

[0010] obtaining a corpus data set, the corpus data set including a plurality of second texts, the text length of the second text being greater than a preset first threshold;

[0011] identifying at least one semantic information associated with the second text, and determining at least one preset emoticon corresponding to each semantic information, respectively;

[0012] performing a vectorization operation on the second text to obtain a first vector corresponding to the second text;

[0013] constructing an emoticon index based on a plurality of first vectors associated with a plurality of second texts in the corpus data set.

[0014] In a third aspect, the embodiments of the present disclosure provide a data processing apparatus, comprising:

[0015] a display module configured to display the conversation text in the conversation interface;

[0016] a processing module configured to display at least one expression item associated with the conversation text in a preset display area in the conversation interface, the expression item being determined from a plurality of preset expressions based on a text length of the conversation text and at least one preset expression association data or current time information;

[0017] a sending module configured to send a first preset expression currently triggered in the conversation interface in response to a triggering operation on the expression item.

[0018] In a fourth aspect, the embodiments of the present disclosure provide a data processing apparatus, comprising:

[0019] an obtaining module configured to obtain a corpus data set, the corpus data set comprising a plurality of second texts, a text length of each second text being greater than a preset first threshold;

[0020] an identifying module configured to identify at least one semantic information associated with each second text, and determine at least one preset expression corresponding to each semantic information, respectively;

[0021] a processing module configured to perform a vectorization operation on each second text to obtain a first vector corresponding to each second text;

[0022] a constructing module configured to construct an expression index based on a plurality of first vectors associated with a plurality of second texts in the corpus data set.

[0023] In a fifth aspect, the embodiments of the present disclosure provide an electronic device, comprising a processor and a memory;

[0024] the memory stores computer-executable instructions;

[0025] the processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the data processing method of the first aspect and various possible designs of the first aspect or the second aspect and various possible designs of the second aspect.

[0026] In a sixth aspect, the embodiments of the present disclosure provide a computer-readable storage medium, the computer-readable storage medium storing computer-executable instructions, when the processor executes the computer-executable instructions, the data processing method of the first aspect and various possible designs of the first aspect or the second aspect and various possible designs of the second aspect is implemented.

[0027] In a seventh aspect, the embodiments of the present disclosure provide a computer program product, including a computer program, which, when executed by a processor, implements the data processing method in the first aspect and various possible designs of the first aspect, or the data processing method in the second aspect and various possible designs of the second aspect.

[0028] The data processing method, device, equipment, computer readable storage medium and product provided by the embodiments of the present disclosure can more flexibly determine the expression item by pre-constructing at least one expression association data, and when the user inputs the conversation text, selecting at least one expression association data based on the length information of the conversation text. Alternatively, the current time information can be determined, and the expression recommendation operation is performed based on the time information, so that the expression recommendation can be more flexible, and the user can be recommended the preset expression more suitable for the current intention of the user after inputting the long conversation text, thereby improving the accuracy of expression recommendation. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor.

[0030] Figure 1 The flowchart of the data processing method provided by the embodiments of the present disclosure is shown.

[0031] Figure 2 The display interface provided by the embodiments of the present disclosure is shown.

[0032] Figure 3 The flowchart of the data processing method provided by another embodiment of the present disclosure is shown.

[0033] Figure 4 Another display interface provided by the embodiments of the present disclosure is shown.

[0034] Figure 5 The flowchart of the data processing method provided by the embodiments of the present disclosure is shown.

[0035] Figure 6 The flowchart of the data processing method provided by another embodiment of the present disclosure is shown.

[0036] Figure 7 The structure diagram of the data processing device provided by the embodiments of the present disclosure is shown.

[0037] Figure 8 The structure diagram of the data processing device provided by the embodiments of the present disclosure is shown.

[0038] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0040] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0041] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0042] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0043] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0044] In instant messaging, users often convey complex meanings through combinations of text and emoticons. For example, a long sentence can express multiple emotions: "I'm very tired from work today, but seeing your message makes me happy" expresses the complex meaning of being tired but happy. Alternatively, users might add emoticons after sending text to reinforce a specific meaning, such as adding a bouquet emoticon after sending "Congratulations!". However, the emoticon recommendation function in existing IM systems has significant limitations: First, it can only process short sentences or single-meaning inputs, failing to analyze the multiple layers of meaning and context in long sentences, leading to a disconnect between the recommendation results and the user's actual needs. For example, current technology only extracts a single keyword in long sentence processing. For instance, the sentence "I'm very tired from work today, but seeing your message makes me happy" can only extract the keyword "happy," failing to analyze multiple layers of meaning, resulting in a disconnect between the recommendation results and the user's true needs. Second, emoticon recommendation only occurs during user input and is based on "replacing text," completely ignoring the high-frequency need for users to add emoticons after sending text to enhance the meaning.

[0045] The technical concept disclosed herein is to construct a hybrid architecture based on "offline preprocessing - online lightweight retrieval". The generative model in the offline stage drives corpus processing and expression matching to build an expression index. Combined with the vector similarity fast retrieval and dual-channel recall mechanism in the online stage, expression recommendation optimization is achieved in high-concurrency scenarios.

[0046] This technical solution focuses on semantic parsing and value assessment in the offline phase. It dynamically adapts to user chat styles through a daily corpus replacement strategy, while simultaneously recalling emoji items online via a dual-channel approach using a mapping database and / or emoji index, balancing recommendation accuracy and response speed. This covers various scenarios, including long sentence parsing and post-text supplementary recommendations, ultimately improving user communication efficiency and the richness of semantic expression.

[0047] To address the technical problem that emoji recommendation functions cannot parse the multiple layers of semantics and context in long sentences, resulting in low accuracy of recommendation results, this disclosure provides a data processing method, apparatus, device, computer-readable storage medium, and product.

[0048] It should be noted that the data processing methods, apparatus, devices, computer-readable storage media, and products provided in this disclosure can be applied to any instant messaging scenario involving emoji recommendations.

[0049] Figure 1 This is a flowchart illustrating the data processing method provided in the embodiments of this disclosure, as shown below. Figure 1 As shown, the method includes:

[0050] Step 101: Display the conversation text in the conversation interface.

[0051] The execution entity in this embodiment is a data processing device, which can be coupled to online devices such as terminal devices.

[0052] In this embodiment, users can communicate instantly with friends within the chat interface. Therefore, the chat interface can display chat text. This chat text can be content entered by the user into the input box but not yet sent. Alternatively, the chat text can be content entered by the user and already sent. Or, the chat text can be chat text sent to a friend with whom the user is having a chat, etc. This disclosure does not impose any limitations on these possibilities.

[0053] Step 102: Display at least one emoticon item associated with the conversation text in a preset display area within the conversation interface. The emoticon item is determined from multiple preset emoticons based on the text length of the conversation text and at least one preset emoticon association data or the current time information.

[0054] In this embodiment, users often have a need to combine text and emoticons during conversations. Therefore, in order to enable users to more quickly determine the preset emoticons that match the currently input conversation text, at least one emoticon item can be determined based on the conversation text, and the at least one emoticon item can be recommended to the user.

[0055] The user-inputted conversation text can be a long text containing a lot of emotions and information, or it can be a shorter text. In order to cover different application scenarios, at least one type of expression association data can be pre-set, so that expression recommendation can be performed based on the length of the conversation text and at least one type of expression association data.

[0056] The emoji association data can be an online mapping database, which may include multiple mapping data pairs. Each mapping data pair may include a first text and its corresponding emoji text. The first text may be conversational text with a length less than or equal to a first threshold. Therefore, when the conversational text entered by the user is relatively short, the emoji item associated with the conversational text can be quickly determined from the online mapping database.

[0057] For example, the first text can be common phrases, such as common emotional expressions like happy, sad, or upset, or common greetings like good morning, good evening, or have you eaten yet.

[0058] The emoji association data can also include an offline emoji index. This can be achieved by accessing a corpus database containing multiple second texts with a length exceeding a first threshold. For each second text, at least one associated semantic information can be identified, and at least one pre-defined emoji can be determined for each semantic information. This allows the establishment of multiple mapping relationships consisting of second texts, semantic information, and pre-defined emojis. To facilitate user retrieval, the second texts can be vectorized, and an emoji index can be constructed based on the first vectors associated with multiple second texts. Thus, when a user inputs long conversational text, the emoji index can retrieve second texts that better fit the conversational text, and emoji recommendations can be performed based on the at least one pre-defined emoji mapped from the second text.

[0059] As one feasible approach, time-limited emoticons can be pre-set. For example, Christmas-related emoticons can be released around Christmas, and Spring Festival-related emoticons can be released around the Spring Festival. Therefore, at least one emoticon can be selected from multiple preset emoticons based on the current time information. For instance, if the conversation text is related to Christmas, and the time information is within the effective time range associated with the time-limited emoticon, then at least one Christmas-related time-limited emoticon can be selected as the current time-limited emoticon.

[0060] Step 103: In response to the triggering operation of the emoticon item, send the first preset emoticon that is currently triggered in the conversation interface.

[0061] In this embodiment, in order to allow users to view the at least one emoticon item more intuitively, at least one emoticon item can be displayed in a preset display area within the conversation interface.

[0062] After displaying at least one emoji item within the preset display area of ​​the chat interface, the user can select any first preset emoji from the at least one emoji item to trigger an action according to actual needs. In response to this trigger action, the first preset emoji can be sent to the chat interface.

[0063] Figure 2 This is a schematic diagram of the display interface provided in the embodiments of this disclosure, such as... Figure 2 As shown, users can input conversation text 22 within the conversation interface 21. To facilitate the expression of current needs by combining text and preset emoticons, at least one emoticon item 23 can also be displayed in the preset display area within the conversation interface 21, so that users can trigger operations on the emoticon item 23 to send the currently selected emoticon item.

[0064] The data processing method provided in this embodiment, by pre-constructing an online mapping database and an offline emoji index, allows for more flexible emoji selection based on the length of the user's conversation text during instant messaging. Alternatively, at least one emoji can be selected based on the current time information, enabling more flexible emoji recommendation.

[0065] Optionally, based on any of the above embodiments, the conversation text includes either a first conversation text entered by the first user or a second conversation text displayed in the conversation interface.

[0066] Step 102 includes:

[0067] Display at least one emoji within the display area associated with the input controls in the conversation interface or within the display area associated with the second conversation text.

[0068] In this embodiment, the conversation text includes either a first conversation text that the first user has entered or a second conversation text displayed in the conversation interface. For example, the conversation text could be content that the user has entered into an input box but has not yet sent. Alternatively, the conversation text could be content that the user has entered and sent. Or, the conversation text could be conversation text sent to a friend with whom the user is having a conversation, etc. This disclosure does not impose any limitations on these aspects.

[0069] Therefore, the at least one emoticon item can be displayed in different display locations depending on the different conversation texts. For example, the conversation text can be generated and sent based on an input control; therefore, at least one emoticon item can be displayed in the display area associated with the input control. Alternatively, the conversation text can be generated and sent by a second user who is having a conversation with the first user; therefore, in response to a preset trigger operation by the first user on the conversation text, at least one emoticon item is displayed in the display area associated with the conversation text. This preset trigger operation can be a long press, double-click, or other trigger operation on the conversation text. Alternatively, the conversation text can include conversation text generated by the first user based on an input control but not sent; therefore, in response to a preset trigger operation by the first user on an emoticon control, an emoticon panel is displayed; and at least one emoticon item is displayed in the emoticon panel.

[0070] For example, the conversation text can be content that the user has entered into the input box but has not yet sent. To make it easier for the user to view the emoticon item, at least one emoticon item can be displayed below the input box. Therefore, the user can add the emoticon item after the conversation text by triggering any emoticon item, and interact with friends by combining text and emoticons.

[0071] To reiterate the example, the conversation text could also be content entered and sent by the user. Therefore, at least one emoji item could be displayed above the content input box, allowing the user to add emojis during the conversation for more accurate emotional expression.

[0072] The data processing method provided in this embodiment can enrich the display content and display style of the conversation interface by displaying at least one emoticon item in different display areas for different types of conversation text.

[0073] Furthermore, based on any of the above embodiments, the method further includes:

[0074] Preprocess the conversation text to obtain the target text.

[0075] The preprocessing operations include one or more of the following: deleting fields in the conversation text that meet the first preset condition, replacing fields in the conversation text that meet the second preset condition with preset replacement text, and standardizing the symbol information of the conversation text.

[0076] In this embodiment, in order to improve the accuracy of subsequent emoji recommendations, after obtaining the conversation text, the conversation text can be preprocessed to obtain the target text.

[0077] The preprocessing operations include one or more of the following: deleting fields in the conversation text that meet the first preset condition, replacing fields in the conversation text that meet the second preset condition with preset replacement text, and standardizing the symbol information of the conversation text.

[0078] The fields that meet the first preset condition can include consecutive numbers or fields containing identification information. The fields that meet the second preset condition can be some infrequently used or discontinued words. The symbol information that needs to be standardized includes, but is not limited to, meaningless symbols such as spaces and consecutive periods.

[0079] The data processing method provided in this embodiment improves the accuracy of subsequent data processing and saves computing resources by preprocessing the conversation text.

[0080] Optionally, based on any of the above embodiments, step 101 includes:

[0081] If the length of the target text is greater than a preset first threshold, then the expression index is used to determine at least one expression item associated with the target text.

[0082] If the length of the target text is less than or equal to a first threshold, a mapping database is used to determine at least one emoji associated with the target text.

[0083] In this embodiment, the conversation text input by the user can be a long conversation text containing a lot of emotions and information, or it can be a relatively short conversation text. In order to cover different application scenarios, a first threshold can be preset, and conversation texts greater than the first threshold can be identified as long conversation texts, while conversation texts less than or equal to the first threshold can be identified as short conversation texts.

[0084] Optionally, long conversation texts generally contain a lot of information. For example, when a user enters "I'm very tired from work today, but seeing your message makes me happy," it can include complex emotions of "tired + happy." In this case, online matching retrieval using a mapping database cannot quickly and accurately obtain the emoticon item. Therefore, an emoticon index can be used to determine at least one emoticon item associated with the target text.

[0085] Short conversation texts generally contain less content, so an online mapping database can be used to recall at least one emoji item.

[0086] The data processing method provided in this embodiment improves recommendation accuracy and scenario coverage through a dual-channel recall mechanism (mapping database + emoji index). Mapping database matching ensures extremely fast matching of high-frequency phrases, while the emoji index adapts to semantic matching of medium- to long sentences. The candidate aggregation step integrates the results of both, avoiding the limitations of a single matching method. This significantly reduces user operation costs and enhances the recommendation efficiency and matching accuracy of adding emojis after text.

[0087] Optionally, based on any of the above embodiments, step 101 includes:

[0088] The expression index is used to identify at least one first expression associated with the target text.

[0089] The target text is segmented to obtain multiple text fragments. A mapping database is used to determine at least one second expression associated with each text fragment.

[0090] At least one expression item is determined based on at least one first expression and at least one second expression.

[0091] In this embodiment, in order to further improve the accuracy of the expression items, a combination of a mapping database and an expression index can be used to jointly determine the expression items.

[0092] Optionally, an emoji index can be used to determine at least one first emoji associated with the target text. Since online mapping databases cannot accurately identify complex, long conversational texts, to improve recommendation accuracy, text segmentation can be performed on the target text to obtain multiple text fragments, and a mapping database can be used to determine at least one second emoji associated with each text fragment. Any text segmentation method can be used to segment the target text, such as punctuation-based segmentation or semantic segmentation, and this disclosure does not impose any limitations on this.

[0093] Furthermore, after determining at least one first expression and at least one second expression respectively, the at least one first expression and at least one second expression can be further filtered to determine at least one expression item.

[0094] The data processing method provided in this embodiment uses a combination of a mapping database and an expression index to determine at least one expression item, thereby further improving the accuracy of expression recommendations.

[0095] Furthermore, based on any of the above embodiments, determining at least one expression item based on at least one first expression and at least one second expression includes:

[0096] The score information of the first expression is determined based on the first association information corresponding to the first expression. The first association information includes the click rate associated with the first expression, the content quality associated with the first expression, and the similarity between the second text associated with the target text determined based on the expression index and the target text.

[0097] The scoring information is determined based on the second association information of the second expression. The second association information includes the first association information, including the click-through rate associated with the first expression and the content quality associated with the first expression.

[0098] Based on a preset sorting method and scoring information, at least one first expression and at least one second expression are sorted to obtain the sorting result.

[0099] At least one first expression and / or second expression that meets the preset filtering conditions in the sorting results are identified as at least one expression item.

[0100] In this embodiment, after determining at least one first expression and at least one second expression respectively, the at least one first expression and at least one second expression can be further filtered to determine at least one expression item.

[0101] Optionally, the score of the first emoticon can be determined based on the first association information corresponding to the first emoticon. The first association information includes the click-through rate associated with the first emoticon, the content quality associated with the first emoticon, and the similarity between the second text associated with the target text (determined based on the emoticon index) and the target text. A higher click-through rate for the first emoticon indicates that it is more frequently used; a higher similarity between the second text and the target text indicates that the first emoticon better meets the user's actual needs. Therefore, based on the click-through rate associated with the first emoticon, the content quality associated with the first emoticon, and the emoticon index, the content quality of each first emoticon and its relevance to the conversation text can be accurately determined.

[0102] The scoring information is determined based on the second association information of the second expression. The second association information includes the first association information, including the click-through rate associated with the first expression and the content quality associated with the first expression.

[0103] Therefore, after calculating the scores for each first expression and each second expression respectively, at least one first expression and at least one second expression can be sorted based on the order of scores from highest to lowest to obtain a sorting result. Then, at least one first expression and / or second expression that meets the preset filtering criteria in the sorting result can be identified as at least one expression item.

[0104] For example, five preset emojis can be recommended to a user at a time, so the top five emojis and / or the second-highest score emojis in the ranking results can be identified as the current emoji items.

[0105] The data processing method provided in this embodiment uses a combination of a mapping database and an emoji index to jointly determine at least one emoji item. When recalling multiple emoji items, the emoji items are filtered based on the score information of the recalled emojis, thereby improving the content quality of the emoji items and enhancing the user experience.

[0106] Figure 3 This is a flowchart illustrating a data processing method provided in yet another embodiment of the present disclosure. Based on any of the above embodiments, as follows... Figure 3 As shown, the facial expression association data includes facial expression indexes. Step 101 includes:

[0107] Step 301: Vectorize the conversation text to obtain the second vector associated with the conversation text.

[0108] Step 302: Determine the first vector that matches the second vector in the expression index through an approximate nearest neighbor search.

[0109] Step 303: Determine at least one preset emoticon associated with the second text corresponding to the first vector as at least one emoticon item.

[0110] In this embodiment, when at least one recommended content is determined using an emoji index, the conversation text can be vectorized to obtain a second vector associated with the conversation text. Any vectorization method can be used to perform the vectorization of the conversation text, and this disclosure does not impose any limitations on this.

[0111] Furthermore, after obtaining the second vector associated with the conversational text, a first vector matching the second vector can be determined in the emoji index through an approximate nearest neighbor search. Since the second text associated with the first vector corresponds to at least one mapping relationship consisting of the second text, semantic information, and preset emojis, at least one preset emoji associated with the second text corresponding to the first vector can be determined as at least one emoji item.

[0112] The data processing method provided in this embodiment vectorizes the conversational text, thus enabling it to quickly and accurately determine the first vector matching the second vector in the emoji index through approximate nearest neighbor search. This allows for the rapid identification of at least one emoji item, improving the fit between the emoji item and the user-input conversational text.

[0113] Furthermore, based on any of the above embodiments, the second text is associated with at least one semantic information, each semantic information is associated with at least one preset emoticon, and the at least one preset emoticon associated with the semantic information is associated with a display order, which is determined based on the click-through rate and content quality of the preset emoticon.

[0114] Step 102 includes:

[0115] For each semantic information, determine the first content to be displayed that meets the display conditions among at least one preset emoticon associated with the semantic information.

[0116] Within the preset display area, the first display content associated with each semantic information is displayed first, and other preset emoticons associated with each semantic information are randomly displayed after the first display content associated with each semantic information.

[0117] In this embodiment, the second text association has at least one semantic information. For example, when constructing an emoji index, a semantic recognition operation needs to be performed on the second text to identify the semantics associated with the second text, thus obtaining different semantic information.

[0118] Therefore, for each semantic information, at least one preset emoticon can be determined corresponding to that voice information. To facilitate the display of emoticons, each preset emoticon associated with each voice information is also associated with a display order, which is determined based on the click-through rate and content quality of the preset emoticons. Among them, preset emoticons with higher click-through rates and higher content quality are displayed earlier.

[0119] Furthermore, for each piece of semantic information, a first display content whose display order satisfies the display conditions is determined from at least one preset emoticon associated with the semantic information. For example, the first display content that satisfies the display conditions can be the preset emoticon that is displayed first among at least one preset emoticon associated with the semantic information.

[0120] To make it easier for users to view higher-quality emoticons, the first content associated with each semantic information can be displayed first in the preset display area, and other preset emoticons associated with each semantic information can be randomly displayed after the first content associated with each semantic information.

[0121] The data processing method provided in this embodiment prioritizes displaying emoticons with higher click rates and content quality, thus enabling users to see higher-quality emoticons in the conversation interface and improving user experience.

[0122] Optionally, based on any of the above embodiments, the facial expression association data includes a mapping database. Step 101 includes:

[0123] Determine the first text corresponding to the session text in the mapping database.

[0124] The preset emojis of the first text mapping are determined as at least one emoji item.

[0125] In this embodiment, when the user inputs short text, at least one emoji item can be determined based on an online mapping database to improve the efficiency of emoji recommendation.

[0126] Optionally, a first text corresponding to the session text can be determined in a mapping database. This determination can be based on the similarity between the session text and each first text in the mapping database.

[0127] Furthermore, since the mapping database includes mapping data pairs consisting of the first text and preset emoticons associated with the first text, after determining the first text corresponding to the conversation text, the preset emoticons mapped to the first text can be determined as at least one emoticon item.

[0128] The data processing method provided in this embodiment determines the first text corresponding to the conversation text in the mapping database for conversation texts with a text length less than a first threshold, thus enabling quick expression recommendation and improving the efficiency of expression recommendation.

[0129] Furthermore, based on any of the above embodiments, the method further includes:

[0130] In response to a triggering action on a preset emoji control within the conversation interface, the emoji panel is displayed.

[0131] Display at least one emoji in the emoji panel.

[0132] In this embodiment, the conversation interface includes an emoji control. In response to a trigger operation on a preset emoji control within the conversation interface, an emoji panel is displayed. Since at least one emoji item can be displayed in the emoji panel, the user can view at least one emoji item more intuitively within the panel.

[0133] Furthermore, based on any of the above embodiments, the preset emoticons include at least one time-limited emoticon item associated with an effective time range. The method further includes:

[0134] Determine the current time information.

[0135] If the current time information is within the effective time range and the conversation text is associated with a timed emoticon, then at least one timed emoticon is identified as at least one emoticon.

[0136] In this embodiment, the preset emoticons also include at least one time-limited emoticon item associated with an effective time range. For example, during Christmas, Christmas-limited emoticons such as Christmas trees and Christmas wreaths can be launched.

[0137] To enable the display of time-limited emojis in the emoji panel and to accurately implement emoji recommendations, a parameter specifying the effective time range can be added to the data package associated with the time-limited emoji item.

[0138] Therefore, when a user opens the emoji panel, the current time information can be determined. If the current time is within the effective time range, at least one time-limited emoji item will be displayed in a designated area of ​​the emoji panel. Conversely, if the current time is outside the effective time range, the time-limited emoji item will not be displayed in the emoji panel.

[0139] Alternatively, after displaying the conversation text within the conversation interface, if it is determined that the current time information is within the effective time range, then at least one time-limited emoticon item can be identified as at least one emoticon item. As one possible approach, if it is determined that the current time information is within the effective time range, and the conversation text is related to the information associated with the time-limited emoticon item, then at least one time-limited emoticon item can be identified as at least one emoticon item. For example, if the time-limited emoticon item is a Spring Festival-limited emoticon, and the conversation text includes phrases such as "Happy Spring Festival" or "Happy Chinese New Year," and the current time information is within the effective time range, then at least one Spring Festival-limited emoticon can be identified as at least one emoticon item.

[0140] Figure 4 This is another schematic diagram of a display interface provided in an embodiment of the present disclosure, such as... Figure 4As shown, an emoji panel 42 can be displayed within the conversation interface 41. If the current time information is within the effective time range of a time-limited emoji item 43, then at least one time-limited emoji item 43 can be displayed within the emoji panel 42.

[0141] The data processing method provided in this embodiment sets an effective time range for time-limited emoticons, thus enabling the accurate display of time-limited emoticons based on this effective time range.

[0142] Figure 5 This is a flowchart illustrating the data processing method provided in the embodiments of this disclosure, as shown below. Figure 5 As shown, the method includes:

[0143] Step 501: Obtain the corpus dataset, which includes multiple second texts, the length of which is greater than a preset first threshold.

[0144] Step 502: Identify at least one semantic information associated with the second text, and determine at least one preset expression corresponding to each semantic information.

[0145] Step 503: Perform vectorization on the second text to obtain the first vector corresponding to the second text.

[0146] Step 504: Construct an expression index based on multiple first vectors associated with multiple second texts in the corpus dataset.

[0147] In this embodiment, the execution entity is a data processing device, which can be coupled to a server. The server processes the second text in the corpus dataset to generate an expression index.

[0148] In this embodiment, a corpus dataset can be obtained, which can be an open-source text dataset. This corpus dataset includes multiple second texts, the length of which is greater than a preset first threshold. That is, the corpus dataset includes multiple long texts.

[0149] Furthermore, for each second text, at least one semantic information associated with it can be identified, and at least one preset emoji can be determined for each semantic information. This allows the establishment of multiple mapping relationships consisting of second text, semantic information, and preset emojis. To facilitate user retrieval, the second text can be vectorized, and an emoji index can be constructed based on the first vectors associated with multiple second texts. Thus, when a user inputs long conversational text, second text that better fits the conversational text can be retrieved based on this emoji index, and emoji recommendation can be performed based on at least one preset emoji mapped from the second text.

[0150] The data processing method provided in this embodiment generates a mapping relationship of "second text → semantic information → preset emoticon" by performing deep semantic parsing on the second text in the corpus dataset, and constructs an emoticon index, thereby supporting rapid retrieval of corpora of millions. For example, when a user inputs "I'm very tired from work today, but seeing your message makes me happy," the method can match the closest second text based on the emoticon index, and then parse out the multi-layered semantics of "tired + happy" based on at least one semantic information associated with the second text, and obtain the preset emoticons associated with each semantic information. This method not only covers the multi-layered semantic parsing needs in long sentences, but also reduces the online computing pressure through an offline-online hybrid architecture, ensuring performance stability in high-concurrency scenarios, and ultimately significantly improving user communication efficiency and the accuracy of semantic expression.

[0151] Furthermore, based on any of the above embodiments, the method further includes:

[0152] Obtain the original dataset, which includes multiple original text corpora.

[0153] Data cleaning operations are performed on the original text corpus to obtain the corpus dataset.

[0154] The data cleaning operation includes one or more of the following: similarity-based deduplication, semantic-based deduplication, deletion of fields in the original corpus text that meet the first preset condition, replacement of fields in the original corpus text that meet the second preset condition with preset replacement text, and standardization of symbol information in the original corpus text.

[0155] In this embodiment, the original open-source dataset can be obtained in advance, and data cleaning operations can be performed on the original dataset to obtain the corpus dataset.

[0156] Optionally, the data cleaning operation includes one or more of the following: similarity-based deduplication, semantic-based deduplication, deletion of fields in the original corpus text that meet a first preset condition, replacement of fields in the original corpus text that meet a second preset condition using preset replacement text, and standardization of symbol information in the original corpus text.

[0157] For example, the similarity between each original text in the original dataset and other original texts can be calculated separately, and duplicate texts from at least two original texts whose similarity exceeds a similarity threshold can be deduplicated. Alternatively, the semantic information of each original text in the original dataset can be determined separately, and duplicate texts from at least two original texts whose semantic information similarity exceeds a similarity threshold can be deduplicated. Alternatively, fields that satisfy the first preset condition can include consecutive numbers or fields that include identification information. Fields that satisfy the second preset condition can be some uncommon or discontinued words. Symbolic information that needs to be standardized includes, but is not limited to, meaningless symbols such as spaces and consecutive periods.

[0158] The data processing method provided in this embodiment removes interference information by cleaning the original dataset, ensuring the quality of the second text used in the semantic parsing process, thereby further improving the accuracy of emoji recommendation and system stability in long sentence scenarios.

[0159] Furthermore, based on any of the above embodiments, step 502 includes:

[0160] The second text and the preset first description information are input into the generative model so that the generative model generates at least one semantic information. The first description information is used to instruct the generative model to identify the semantics in the second text.

[0161] In this embodiment, to quickly and accurately identify the semantic information associated with the second text, a generative model can be used to perform semantic recognition on the second text. The generative model includes, but is not limited to, large language models and other network models capable of content generation.

[0162] Optionally, the second text and the preset first descriptive information can be input into the generative model so that the generative model generates at least one semantic information, and the first descriptive information is used to instruct the generative model to identify the semantics in the second text.

[0163] The data processing method provided in this embodiment uses a generative model to deeply analyze the semantics and context of text, generating accurate semantic features. Based on these semantic features, at least one preset emoji can be matched more accurately, thereby improving the accuracy of subsequent emoji recommendations.

[0164] Furthermore, based on any of the above embodiments, step 502 includes:

[0165] The semantic information and the preset emoji data package are input into the preset classification model to obtain at least one preset emoji output by the classification model that corresponds to the semantic information.

[0166] In this embodiment, a classification model can be used to match semantic information with preset expressions.

[0167] Optionally, semantic information and a preset emoji data package can be input into a preset classification model to obtain at least one preset emoji output by the classification model that corresponds to the semantic information. The emoji data package includes multiple preset emojis, including but not limited to symbolic emojis and user-defined emojis. The classification model can be a pre-trained network model capable of matching semantic information with preset emojis.

[0168] The data processing method provided in this embodiment, by pre-setting a classification model, can more accurately match at least one preset expression corresponding to the semantic information after the semantic information is identified, thereby further improving the accuracy of expression recommendation and system stability in long sentence scenarios.

[0169] Figure 6 This is a flowchart illustrating a data processing method provided in yet another embodiment of the present disclosure. Based on any of the above embodiments, as follows... Figure 6 As shown, the method also includes:

[0170] Step 601: Obtain the association data of each second text in the corpus dataset. The association data includes one or more of the following: usage frequency, time decay parameter, and age penalty parameter corresponding to the second text.

[0171] Step 602: Update the second text in the corpus dataset based on the associated data according to the preset time interval.

[0172] In this embodiment, in order to make the emoji recommendation operation more adaptable to changes in the user's chat style and to recommend newer and higher-quality emojis to the user, the second text in the corpus dataset can also be updated at preset time intervals.

[0173] Optionally, association data for each second text in the corpus dataset can be obtained. This association data includes one or more of the following: usage frequency, time decay parameter, and age penalty parameter corresponding to the second text. The text value of the second text can be calculated by combining the usage frequency, time decay parameter, and age penalty parameter.

[0174] Therefore, after determining the association parameters of the second text, the second text in the corpus dataset can be updated based on the association data at preset time intervals.

[0175] The data processing method provided in this embodiment adjusts the second text in the corpus dataset based on the associated data of the second text, eliminates inefficient second text, and updates and adds commonly used words, such as emerging internet slang, to the corpus dataset, thereby dynamically adapting to changes in the user's chat style and improving the accuracy of emoji recommendations.

[0176] Furthermore, based on any of the above embodiments, step 602 includes:

[0177] Get multiple newly added and frequently used words in the conversation of the user group within a preset time interval.

[0178] The updated data associated with the second text is calculated based on the associated data of the second text and a preset algorithm.

[0179] Sort the multiple second texts in descending order of the updated data.

[0180] Replace multiple second texts that are ranked lower in the order based on several newly added commonly used words.

[0181] In this embodiment, users' chat styles may change, resulting in the generation of newly added frequently used words. Therefore, it is possible to obtain multiple newly added frequently used words from the user group during the conversation within a preset time interval. This preset time interval can be 24 hours, thus enabling daily updates to the corpus database.

[0182] Furthermore, updated data relating to the second text can be calculated based on the associated data of the second text and a preset algorithm. This updated data can be the text value of the second text.

[0183] Furthermore, multiple secondary texts can be sorted in descending order of updated data. Then, multiple secondary texts at the bottom of the sorted list can be replaced based on several newly added commonly used words. For example, if 2000 new commonly used words were added that day, the 2000 secondary texts at the bottom of the sorted list can be replaced based on these newly added commonly used words.

[0184] The data processing method provided in this embodiment replaces inefficient second text in the corpus dataset based on newly added common words, thereby enabling the second text in the corpus dataset to dynamically adapt to changes in the user's chat style. This allows for dynamic updates of the emoji index, second text → semantic information → preset emoji mapping, further improving the accuracy of emoji recommendations.

[0185] Figure 7 This is a schematic diagram of the structure of the data processing apparatus provided in the embodiments of this disclosure, such as... Figure 7As shown, the device includes: a display module 71, a processing module 72, and a sending module 73. The determining module 71 is used to display conversation text in the conversation interface. The display module 72 is used to display at least one emoticon item associated with the conversation text within a preset display area in the conversation interface. The emoticon item is determined from multiple preset emoticons based on the text length of the conversation text and at least one preset emoticon association data or current time information. The sending module 73 is used to send the currently triggered first preset emoticon within the conversation interface in response to a triggering operation on the emoticon item.

[0186] Furthermore, based on any of the above embodiments, the conversation text includes a first conversation text that has been entered by the first user or a second conversation text displayed in the conversation interface; the processing module is configured to: display at least one emoticon item in the display area associated with the input control of the conversation interface or in the associated area of ​​the second conversation text.

[0187] Furthermore, based on any of the above embodiments, the preset emoticons include at least one time-limited emoticon item associated with an effective time range; the data processing device further includes: a determining module, used to determine the current time information; and a processing module, used to determine at least one time-limited emoticon item as at least one emoticon item in response to the current time information being within the effective time range and the conversation text being associated with the time-limited emoticon item.

[0188] Furthermore, based on any of the above embodiments, the expression association data includes an online mapping database and / or an offline expression index; wherein, the mapping database includes multiple sets of mapping data pairs consisting of first text with a text length less than or equal to a first threshold and preset expressions associated with the first text, and the expression index is constructed based on first vectors associated with multiple second texts with a text length greater than the first threshold, and the second text association has at least one preset expression.

[0189] Furthermore, based on any of the above embodiments, the data processing apparatus further includes: a preprocessing module, used to perform preprocessing operations on the conversation text to obtain target text. The preprocessing operations include one or more of the following: deleting fields in the conversation text that meet a first preset condition, replacing fields in the conversation text that meet a second preset condition with preset replacement text, and standardizing the symbol information of the conversation text.

[0190] Furthermore, based on any of the above embodiments, the determining module is configured to: in response to the target text having a text length greater than a preset first threshold, determine at least one emoticon associated with the target text using an emoticon index; and in response to the target text having a text length less than or equal to the first threshold, determine at least one emoticon associated with the target text using a mapping database.

[0191] Furthermore, based on any of the above embodiments, if the length of the target text is greater than a preset first threshold, the determining module is configured to: determine at least one first emoticon associated with the target text using an emoticon index; perform text segmentation on the target text to obtain multiple text segments; determine at least one second emoticon associated with each text segment using a mapping database; and determine at least one emoticon item based on at least one first emoticon and at least one second emoticon.

[0192] Further, based on any of the above embodiments, a determining module is configured to: determine the score information of the first expression based on the first association information corresponding to the first expression, wherein the first association information includes the click-through rate associated with the first expression, the content quality associated with the first expression, and the similarity between the second text associated with the target text determined based on the expression index and the target text; determine the score information based on the second association information of the second expression, wherein the second association information includes the click-through rate associated with the first expression and the content quality associated with the first expression; sort at least one first expression and at least one second expression based on a preset sorting method and the score information to obtain a sorting result; and determine at least one first expression and / or second expression that meets the preset filtering conditions in the sorting result as at least one expression item.

[0193] Furthermore, based on any of the above embodiments, the facial expression association data includes an facial expression index. The determining module is configured to: perform vectorization processing on the conversation text to obtain a second vector associated with the conversation text; determine a first vector matching the second vector in the facial expression index through an approximate nearest neighbor search; and determine at least one preset facial expression associated with the second text corresponding to the first vector as at least one facial expression item.

[0194] Furthermore, based on any of the above embodiments, the second text is associated with at least one semantic information, each semantic information is associated with at least one preset emoticon, and the at least one preset emoticon associated with the semantic information is associated with a display order, which is determined based on the click-through rate and content quality of the preset emoticons. The determining module is used to: for each semantic information, determine the first display content whose display order meets the display conditions among the at least one preset emoticon associated with the semantic information; prioritize displaying the first display content associated with each semantic information within a preset display area; and randomly display other preset emoticons associated with each semantic information after the first display content associated with each semantic information.

[0195] Furthermore, based on any of the above embodiments, the expression association data includes a mapping database. A determining module is configured to: determine a first text corresponding to the conversational text in the mapping database; and determine a preset expression mapped to the first text as at least one expression item.

[0196] Furthermore, based on any of the above embodiments, the data processing device further includes: a response module, configured to display an emoji panel in response to a trigger operation on a preset emoji control within the session interface; and a display module, configured to display at least one emoji item within the emoji panel.

[0197] Furthermore, based on any of the above embodiments, the preset emoticons also include at least one time-limited emoticon item associated with an effective time range. The data processing device further includes: a determining module, used to determine the current time information; and a display module, used to display at least one time-limited emoticon item in the emoticon panel in response to the current time information being within the effective time range.

[0198] Figure 8 This is a schematic diagram of the structure of the data processing apparatus provided in the embodiments of this disclosure, such as... Figure 8 As shown, the device includes: an acquisition module 81, a recognition module 82, a processing module 83, and a construction module 84. The acquisition module 81 is used to acquire a corpus dataset, which includes multiple second texts, each with a length greater than a preset first threshold. The recognition module 82 is used to recognize at least one semantic information associated with each second text, and to determine at least one preset expression corresponding to each semantic information. The processing module 83 is used to perform vectorization operations on the second texts to obtain a first vector corresponding to each second text. The construction module 84 is used to construct an expression index based on the multiple first vectors associated with the multiple second texts in the corpus dataset.

[0199] Furthermore, based on any of the above embodiments, the data processing device further includes: an acquisition module, used to acquire an original dataset, the original dataset including multiple original corpus texts; and a cleaning module, used to perform data cleaning operations on the original corpus texts to obtain a corpus dataset. The data cleaning operations include one or more of the following: similarity-based deduplication, semantic-based deduplication, deletion of fields in the original corpus text that meet a first preset condition, replacement of fields in the original corpus text that meet a second preset condition using preset replacement text, and standardization of symbolic information in the original corpus text.

[0200] Furthermore, based on any of the above embodiments, the recognition module is configured to: input the second text and preset first description information into the generative model, so that the generative model generates at least one semantic information, wherein the first description information is used to instruct the generative model to recognize the semantics in the second text.

[0201] Furthermore, based on any of the above embodiments, the recognition module is used to: input semantic information and a preset emoji data package into a preset classification model to obtain at least one preset emoji output by the classification model that corresponds to the semantic information.

[0202] Furthermore, based on any of the above embodiments, the data processing apparatus further includes: an acquisition module, configured to acquire associated data of each second text in the corpus dataset, the associated data including one or more of the following: usage frequency, time decay parameter, and age penalty parameter corresponding to the second text; and an update module, configured to update the second text in the corpus dataset based on the associated data at preset time intervals.

[0203] Furthermore, based on any of the above embodiments, the update module is configured to: obtain multiple newly added frequently used words in the user group during the conversation within a preset time interval; calculate the updated data associated with the second text based on the association data of the second text and a preset algorithm; sort the multiple second texts in descending order of the updated data; and replace the multiple second texts that are ranked lower based on the multiple newly added frequently used words.

[0204] The device provided in this embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0205] To implement the above embodiments, this disclosure also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the data processing method as described in any of the above embodiments.

[0206] To implement the above embodiments, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the data processing method as described in any of the above embodiments.

[0207] To implement the above embodiments, this disclosure also provides an electronic device, including: a processor and a memory;

[0208] The memory stores instructions that the computer executes;

[0209] The processor executes computer execution instructions stored in memory, causing the processor to perform the data processing method as described in any of the above embodiments.

[0210] Figure 9This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. The electronic device 900 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable media players (PMPs), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 9 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0211] like Figure 9 As shown, the electronic device 900 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device 900. The processing unit 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0212] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic device 900 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 9 An electronic device 900 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0213] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by a processing device 901, it performs the functions defined in the methods of embodiments of this disclosure.

[0214] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0215] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0216] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0217] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0218] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0219] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0220] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0221] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0222] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0223] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0224] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A data processing method, characterized in that, include: Display the conversation text in the conversation interface; At least one emoticon item associated with the conversation text is displayed in a preset display area within the conversation interface. The emoticon item is determined from multiple preset emoticons based on the text length of the conversation text and at least one preset emoticon association data or the current time information. In response to the triggering operation of the emoticon item, the currently triggered first preset emoticon is sent within the conversation interface.

2. The method according to claim 1, characterized in that, The conversation text includes either the first conversation text entered by the first user or the second conversation text displayed in the conversation interface. Displaying at least one emoticon associated with the conversation text within a preset display area in the conversation interface includes: At least one emoticon item is displayed in the display area associated with the input control in the conversation interface or in the display area associated with the second conversation text.

3. The method according to claim 1, characterized in that, The preset emoticons include at least one time-limited emoticon item associated with an effective time range; the method further includes: Determine the current time information; In response to the current time information being within the effective time range and the conversation text being associated with the time-limited emoticon item, the at least one time-limited emoticon item is determined as the at least one emoticon item.

4. The method according to claim 1, characterized in that, The facial expression association data includes an online mapping database and / or an offline facial expression index; The mapping database includes multiple sets of mapping data pairs consisting of first texts with a text length less than or equal to a first threshold and preset emoticons associated with the first texts. The emoticon index is constructed based on first vectors associated with multiple second texts with a text length greater than the first threshold, and the second texts are associated with at least one preset emoticon.

5. The method according to claim 1, characterized in that, The method further includes: The conversation text is preprocessed to obtain the target text; The preprocessing operation includes one or more of the following: deleting fields in the conversation text that meet a first preset condition, replacing fields in the conversation text that meet a second preset condition with preset replacement text, and standardizing the symbol information of the conversation text.

6. The method according to claim 5, characterized in that, The method further includes: If the length of the target text is greater than a preset first threshold, then at least one emoji item associated with the target text is determined using an emoji index. In response to the target text having a length less than or equal to the first threshold, at least one emoji item associated with the target text is determined using a mapping database.

7. The method according to claim 1, characterized in that, The method further includes: Emoticon indexing is used to identify at least one first emoticon associated with the target text; The target text is segmented to obtain multiple text fragments, and a mapping database is used to determine at least one second expression associated with each text fragment. The at least one expression item is determined based on the at least one first expression and the at least one second expression.

8. The method according to claim 7, characterized in that, Determining the at least one expression item based on the at least one first expression and the at least one second expression includes: The score information of the first expression is determined based on the first association information corresponding to the first expression. The first association information includes the click-through rate associated with the first expression, the content quality associated with the first expression, and the similarity between the second text associated with the target text and the target text determined based on the expression index. The score information is determined based on the second association information of the second expression, wherein the second association information includes the click-through rate associated with the first expression and the content quality associated with the first expression; Based on a preset sorting method and the scoring information, the at least one first expression and at least one second expression are sorted to obtain a sorting result; At least one first expression and / or second expression that meets the preset filtering conditions in the sorting results are identified as the at least one expression item.

9. The method according to claim 1, characterized in that, The facial expression association data includes an facial expression index; the method further includes: The conversation text is vectorized to obtain a second vector associated with the conversation text; A first vector matching the second vector is determined in the expression index by an approximate nearest neighbor search; At least one preset emoticon associated with the second text corresponding to the first vector is determined as the at least one emoticon item.

10. The method according to claim 9, characterized in that, The second text is associated with at least one semantic information, and each semantic information is associated with at least one preset emoticon. The at least one preset emoticon associated with the semantic information is associated with a display order, which is determined based on the click-through rate and content quality of the preset emoticon. Displaying at least one emoticon associated with the conversation text within a preset display area in the conversation interface includes: For each semantic information, determine the first display content that satisfies the display conditions from at least one preset expression associated with the semantic information; Within the preset display area, the first display content associated with each semantic information is displayed first, and other preset expressions associated with each semantic information are randomly displayed after the first display content associated with each semantic information.

11. The method according to claim 1, characterized in that, The facial expression association data includes a mapping database; the method also includes... Determine the first text corresponding to the session text in the mapping database; The preset emoticon of the first text mapping is determined as the at least one emoticon item.

12. A data processing method, characterized in that, include: Obtain a corpus dataset, which includes multiple second texts, the length of which is greater than a preset first threshold. Identify at least one semantic information associated with the second text, and determine at least one preset expression corresponding to each semantic information; Perform vectorization on the second text to obtain the first vector corresponding to the second text; An expression index is constructed based on multiple first vectors associated with multiple second texts in the corpus dataset.

13. A data processing apparatus, characterized in that, include: The display module is used to display the conversation text in the conversation interface; The processing module is configured to display at least one emoticon item associated with the conversation text within a preset display area in the conversation interface. The emoticon item is determined from multiple preset emoticons based on the text length of the conversation text and at least one preset emoticon association data or current time information. The sending module is used to send the currently triggered first preset emoticon within the conversation interface in response to the triggering operation of the emoticon item.

14. An electronic device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the data processing method as described in any one of claims 1 to 11 or 12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the data processing method as described in any one of claims 1 to 11 or 12.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the data processing method as described in any one of claims 1 to 11 or 12.

Images