Methods, devices, storage media, and electronic devices for acquiring emoji combinations

Abstract

This disclosure relates to a method, apparatus, storage medium, and electronic device for obtaining emoji combinations. The method includes: obtaining multiple candidate emoji combinations from multiple target texts, each candidate emoji combination comprising multiple emojis; for each candidate emoji combination, obtaining one or more adjacent characters from the multiple target texts adjacent to the candidate emoji combination, and obtaining the adjacent character richness of the candidate emoji combination based on the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination; obtaining the dependency of the candidate emoji combination based on the probability of the multiple emojis of the candidate emoji combination appearing individually in the multiple target texts and the probability of the candidate emoji combination appearing in the multiple target texts; and determining a target emoji combination based on the adjacent character richness and dependency of each candidate emoji combination.

Description

Technical Field

[0001] This disclosure relates to the field of natural language processing, and more specifically, to a method, apparatus, storage medium, and electronic device for acquiring combinations of emojis. Background Technology

[0002] With the development of internet technology, especially the widespread use of social media apps and e-commerce apps, many people use emojis instead of Chinese words to express specific meanings for easier communication. Acquiring and translating these emojis is beneficial for effective big data analysis of online language, enabling aspects such as sentiment analysis, opinion analysis, market trend analysis, behavior prediction, and human-computer interaction.

[0003] In practical applications, besides using a single emoticon to represent a specific meaning, multiple emoticons can be combined into an emoticon combination, which can more fully express a meaning. To analyze online language, it's necessary to discover these emoticon combinations from online language data. In related technologies, emoticon combinations can be manually collected from the internet and compiled into a symbol dictionary, which can then be used to statistically analyze the application of emoticons online. However, because emoticons are a relatively new form of online language, and new emoticon combinations are constantly emerging, manual collection is not only inefficient but also makes it difficult to discover new emoticon combinations in a timely manner. Summary of the Invention

[0004] To overcome the aforementioned problems in related technologies, this disclosure provides a method, apparatus, storage medium, and electronic device for obtaining combinations of emojis.

[0005] According to a first aspect of the present disclosure, a method for obtaining a combination of emojis is provided, the method comprising:

[0006] Multiple candidate emoji combinations are obtained from multiple target texts, wherein the candidate emoji combinations include multiple emojis;

[0007] For each candidate emoji combination, one or more adjacent characters are obtained from multiple target texts. The richness of adjacent characters for the candidate emoji combination is obtained based on the number of these adjacent characters and the probability of each adjacent character being adjacent to the candidate emoji combination. Furthermore, the dependency between the multiple emojis in the candidate emoji combination is obtained based on the probability of each emoji appearing individually in multiple target texts and the probability of the candidate emoji combination appearing in multiple target texts. The one or more adjacent characters are one or more non-repeating characters obtained by deduplicating the characters adjacent to the candidate emoji combination in the multiple target texts.

[0008] The target emoji combination is determined from the plurality of candidate emoji combinations based on the richness of adjacent characters and the dependency of each candidate emoji combination.

[0009] Optionally, the adjacent characters include a first adjacent character and a second adjacent character, wherein the first adjacent character is the character adjacent to a first side of the candidate emoji combination, and the second adjacent character is the character adjacent to a second side of the candidate emoji combination; obtaining the adjacent character richness of the candidate emoji combination based on the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination includes:

[0010] Based on the number of the first adjacent characters and the first adjacent probability of each first adjacent character with the candidate emoji combination, the richness of the first adjacent characters of the candidate emoji combination is calculated.

[0011] The richness of the second adjacent characters of the candidate emoji combination is calculated based on the number of the second adjacent characters and the second adjacent probability of each second adjacent character with the candidate emoji combination.

[0012] The adjacent character richness is calculated based on the first adjacent character richness and the second adjacent character richness.

[0013] Optionally, obtaining the dependency between the multiple emojis of the candidate emoji combination based on the probability of each emoji appearing individually in the multiple target texts and the probability of the candidate emoji combination appearing in the multiple target texts includes:

[0014] Obtain the first probability of the candidate emoji combination appearing in multiple target texts;

[0015] Obtain the second probability of each emoji in the candidate emoji combination appearing in multiple target texts;

[0016] The dependency of the candidate emoji combination is calculated based on the first probability, the second probability, and the number of emojis in the candidate emoji combination.

[0017] Optionally, determining the target emoji combination from the multiple candidate emoji combinations based on the adjacent character richness and the dependency of each candidate emoji combination includes:

[0018] For each candidate emoji combination, the combination score of the candidate emoji combination is calculated based on the richness of adjacent characters and the dependency of the candidate emoji combination.

[0019] Sort the multiple candidate emoji combinations according to the combination score;

[0020] The first few candidate emojis in the sorting results are combined to form the target emoji combination.

[0021] According to a second aspect of the present disclosure, an apparatus for acquiring combinations of emojis is provided, the apparatus comprising:

[0022] The candidate emoji combination acquisition module is configured to acquire multiple candidate emoji combinations from multiple target texts, wherein the candidate emoji combinations include multiple emojis;

[0023] The candidate emoji combination analysis module is configured to, for each candidate emoji combination, obtain one or more adjacent characters from multiple target texts that are adjacent to the candidate emoji combination, and obtain the adjacent character richness of the candidate emoji combination based on the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination, and obtain the dependency between the multiple emojis of the candidate emoji combination based on the probability of the multiple emojis of the candidate emoji combination appearing individually in multiple target texts and the probability of the candidate emoji combination appearing in multiple target texts; wherein, the one or more adjacent characters are one or more non-repeating characters obtained after deduplicating the characters adjacent to the candidate emoji combination in multiple target texts;

[0024] The target emoji combination determination module is configured to determine a target emoji combination from a plurality of candidate emoji combinations based on the adjacent character richness and the dependency of each candidate emoji combination.

[0025] Optionally, the adjacent characters include a first adjacent character and a second adjacent character, wherein the first adjacent character is the character adjacent to the first side of the candidate emoji combination, and the second adjacent character is the character adjacent to the second side of the candidate emoji combination; the candidate emoji combination analysis module is configured to:

[0026] Based on the number of the first adjacent characters and the first adjacent probability of each first adjacent character with the candidate emoji combination, the richness of the first adjacent characters of the candidate emoji combination is calculated.

[0027] The richness of the second adjacent characters of the candidate emoji combination is calculated based on the number of the second adjacent characters and the second adjacent probability of each second adjacent character with the candidate emoji combination.

[0028] The adjacent character richness is calculated based on the first adjacent character richness and the second adjacent character richness.

[0029] Optionally, the candidate emoji combination analysis module is configured as follows:

[0030] Obtain the first probability of the candidate emoji combination appearing in multiple target texts;

[0031] Obtain the second probability of each emoji in the candidate emoji combination appearing in multiple target texts;

[0032] The dependency of the candidate emoji combination is calculated based on the first probability, the second probability, and the number of emojis in the candidate emoji combination.

[0033] Optionally, the target emoji combination determination module is configured to...

[0034] For each candidate emoji combination, the combination score of the candidate emoji combination is calculated based on the richness of adjacent characters and the dependency of the candidate emoji combination.

[0035] Sort the multiple candidate emoji combinations according to the combination score;

[0036] The first few candidate emojis in the sorting results are combined to form the target emoji combination.

[0037] According to a third aspect of the present disclosure, an electronic device is provided, comprising:

[0038] processor;

[0039] Memory used to store processor-executable instructions;

[0040] The processor is configured to perform the steps of the method for obtaining emoji combinations provided in the first aspect of this disclosure.

[0041] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of the method for obtaining emoji combinations provided in the first aspect of the present disclosure.

[0042] The technical solution provided by the embodiments of this disclosure can include the following beneficial effects: obtaining multiple candidate emoji combinations from multiple target texts, each candidate emoji combination including multiple emojis; for each candidate emoji combination, obtaining one or more adjacent characters adjacent to the candidate emoji combination from the multiple target texts, and obtaining the adjacent character richness of the candidate emoji combination based on the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination; and obtaining the dependency between the multiple emojis of the candidate emoji combination based on the probability of the multiple emojis of the candidate emoji combination appearing individually in the multiple target texts and the probability of the candidate emoji combination appearing in the multiple target texts; wherein, the one or more adjacent characters are one or more non-repeating characters obtained after deduplicating the characters adjacent to the candidate emoji combination in the multiple target texts; and determining the target emoji combination from the multiple candidate emoji combinations based on the adjacent character richness and dependency of each candidate emoji combination. In this way, through unsupervised mining, target emoji combinations can be efficiently obtained from a large amount of target text based on adjacent character richness and dependency.

[0043] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0045] Figure 1 This is a flowchart illustrating a method for obtaining a combination of emojis according to an exemplary embodiment.

[0046] Figure 2 This is a block diagram illustrating an apparatus for acquiring a combination of emojis according to an exemplary embodiment.

[0047] Figure 3 This is a block diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0049] First, the application scenarios of this disclosure will be explained. This disclosure can be applied to scenarios involving obtaining combinations of emojis. With the development of network technology, in addition to using a single emoji to represent a certain meaning, people can also use combinations of emojis to identify a certain meaning. An emoji combination is formed by merging multiple interdependent emojis together, and this combination can more fully express a meaning. For example, a certain internet slang term includes "The photo quality looks a bit off." "Want to get a new phone", where: a single emoji "" represents "chili pepper", a single emoji It means "chicken"; but it will While viewed as a combination of emoticons, it actually represents "garbage." To analyze online language, it's necessary to mine these emoticon combinations from online language data. One approach is to manually collect emoticon combinations from the internet and create a symbol dictionary, which can then be used to analyze their application online. Another approach is to use artificial intelligence models to acquire emoticon combinations from the internet and analyze their application. However, these AI models require supervised training based on sample data, which also requires manual collection. But because emoticons are a relatively new form of online language, and new emoticon combinations are constantly emerging, manual collection is not only inefficient but also makes it difficult to discover new emoticon combinations in a timely manner.

[0050] To address the aforementioned issues, this disclosure provides a method, apparatus, storage medium, and electronic device for obtaining emoji combinations. Employing an unsupervised mining approach, it can efficiently extract emoji combinations from a large amount of online language.

[0051] The present disclosure will now be described in conjunction with specific embodiments.

[0052] Figure 1 This disclosure provides a method for obtaining combinations of emojis, such as... Figure 1 As shown, the method may include:

[0053] S101. Obtain multiple candidate emoji combinations from multiple target texts, wherein the candidate emoji combination includes multiple emojis.

[0054] The multiple target texts can be internet slang obtained from the internet, such as chat statements obtained from social media apps or e-commerce apps. Each target text may contain emojis; alternatively, some target texts may contain emojis while others do not.

[0055] The candidate emoji combination includes at least two consecutive emojis. For example, a simple traversal search can be used to select N consecutive emojis present in multiple target texts as the candidate emoji combination, where N can be any positive integer greater than or equal to 2.

[0056] Furthermore, when N is greater than or equal to 3, the N emojis can be arranged and combined to obtain more emoji combinations. For example: if the target text contains four consecutive emojis "△○□☆", which means N is 4, the following six emoji combinations can be obtained by arranging and combining these four emojis: "△○", "△○□", "△○□☆", "○□", "○□☆", and "□☆".

[0057] Furthermore, to reduce the complexity of the traversal search, the maximum value of N can be limited. Consecutive emojis exceeding this maximum value can be ignored and not processed. For example, the maximum value of N can be 8, meaning that the maximum number of emojis included in the obtained candidate emoji combinations is 8.

[0058] S102. For each candidate emoji combination, obtain the richness of adjacent characters of the candidate emoji combination and the dependency between multiple emojis in the candidate emoji combination.

[0059] In this step, the richness of adjacent characters for the candidate emoji combination can be obtained as follows: One or more adjacent characters are obtained from multiple target texts that are adjacent to the candidate emoji combination. Based on the number of these adjacent characters and the probability of each adjacent character being adjacent to the candidate emoji combination, the richness of adjacent characters for the candidate emoji combination is obtained. Here, the one or more adjacent characters are one or more non-repeating characters obtained by deduplicating the characters adjacent to the candidate emoji combination in multiple target texts.

[0060] The dependency between multiple emojis in a candidate emoji combination can be obtained in the following way: based on the probability of each emoji in the candidate emoji combination appearing individually in multiple target texts and the probability of the candidate emoji combination appearing in multiple target texts, the dependency between multiple emojis in the candidate emoji combination can be obtained.

[0061] Among them, the above adjacent characters can be one or more of Chinese characters, English letters, Arabic numerals, punctuation marks, spaces, and emojis.

[0062] Exemplarily, in each target text containing the candidate emoji, two adjacent characters adjacent to the candidate emoji can be obtained. For example: if the target text is "one two □☆ three four" and the candidate emoji is "□☆", then the adjacent characters of the candidate emoji are "two" and "three". Another example: if the target text is "□☆ three four" and the candidate emoji is "□☆", then the adjacent character of the candidate emoji is "three".

[0063] S103. Determine the target emoji combination from multiple candidate emoji combinations according to the richness and dependence of the adjacent characters of each candidate emoji combination.

[0064] In this step, there can be multiple ways to determine the target emoji combination. Exemplarily:

[0065] Two parameters, namely a preset richness threshold and a preset dependence threshold, can be preset in advance. The candidate emoji combinations with adjacent character richness greater than or equal to the preset richness threshold, and / or dependence greater than or equal to the preset dependence threshold are used as the above target emoji combinations.

[0066] It is also possible to sort the candidate emoji combinations according to the adjacent character richness or dependence respectively, and use the candidate emoji combinations ranked in the top M in terms of adjacent character richness, and / or the top M in terms of dependence as the above target emoji combinations.

[0067] Using the above method, multiple candidate emoji combinations are obtained from multiple target texts. The candidate emoji combination includes multiple emojis; for each candidate emoji combination, one or more adjacent characters adjacent to the candidate emoji combination are obtained from multiple such target texts, and according to the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination, the richness of the adjacent characters of the candidate emoji combination is obtained. And according to the probability of each emoji in the candidate emoji combination appearing alone in multiple such target texts and the probability of the candidate emoji combination appearing in multiple such target texts, the dependence between the multiple emojis in the candidate emoji combination is obtained; among them, the one or more adjacent characters are one or more non-repeated characters obtained by de-duplicating the characters adjacent to the candidate emoji combination in multiple such target texts; the target emoji combination is determined from multiple candidate emoji combinations according to the richness and dependence of the adjacent characters of each candidate emoji combination. In this way, through the unsupervised mining method, the target emoji combination can be efficiently obtained from a large number of target texts according to the richness and dependence of the adjacent characters.

[0068] In another embodiment of the present disclosure, the adjacent characters include a first adjacent character and a second adjacent character. The first adjacent character is the character adjacent to the first side of the candidate emoji combination, and the second adjacent character is the character adjacent to the second side of the candidate emoji combination.

[0069] Exemplarily, if the target text is arranged horizontally from left to right, the first side may be the left side, the second side may be the right side, the first adjacent character of the candidate emoji combination may be the character adjacent to the left of the candidate emoji combination; the second adjacent character of the candidate emoji combination may be the character adjacent to the right of the candidate emoji combination. For example, if the target text is "one two □☆ three four", and the candidate emoji is "□☆", then the first adjacent character (i.e., the left adjacent character) of the candidate emoji is "two", and the second adjacent character (i.e., the right adjacent character) of the candidate emoji is "three".

[0070] Of course, in another example, if the target text is arranged vertically from top to bottom, the first side may be the upper side, the second side may be the lower side, the first adjacent character of the candidate emoji combination may be the character adjacent to the upper of the candidate emoji combination; the second adjacent character of the candidate emoji combination may be the character adjacent to the lower of the candidate emoji combination. <00​​​​​​​​​​​​​​​​​​​The richness of the first adjacent character can be calculated according to the following formula (1):

[0077]

[0078] Where E1 represents the richness of the first adjacent character of the candidate emoji combination, wa i This represents the first adjacent character of the i-th element, where i ranges from 1 to m. P(wa) i |C) represents the i-th first adjacent character wa in multiple target texts. i The probability of the candidate emoji combination C appearing on the first side.

[0079] Furthermore, the above P(wa) i |C) can be obtained as follows: Let X1 be the number of times the candidate emoji combination C appears in multiple target texts. In these X1 occurrences, the first adjacent character wa... i If the number of times the candidate emoji combination C appears on the first side is X2, then the quotient obtained by dividing X2 by X1 can be used as the aforementioned P(wa i |C).

[0080] It should be noted that the richness of the first adjacent character can also be called the first adjacent information entropy. According to the above formula (1), the larger the number m of the first adjacent character, or the greater the probability of the first adjacent character appearing on the first side of the candidate emoji combination C, the higher the richness of the first adjacent character.

[0081] The richness of the second adjacent character can be calculated using the following formula (2):

[0082]

[0083] Where E2 represents the richness of the first adjacent character of the candidate emoji combination, wb j This represents the j-th second adjacent character, where j ranges from 1 to n, P(wb j |C) represents the j-th second adjacent character wb in multiple target texts. j The probability of the candidate emoji combination C appearing on the second side.

[0084] Similarly, the above P(wb) j |C) can be obtained as follows: Let X1 be the number of times the candidate emoji combination C appears in multiple target texts. In these X1 occurrences, the second adjacent character wb... j If the number of times the candidate emoji combination C appears on the second side is X3, then the quotient obtained by dividing X3 by X1 can be used as the aforementioned P(wb) j |C).

[0085] It should also be noted that the above-mentioned second adjacent character richness can also be called the second adjacent information entropy. According to the above formula (2), the larger the number of second adjacent characters n, or the greater the probability of the second adjacent characters appearing on the second side of the candidate emoji combination C, the higher the richness of the second adjacent characters.

[0086] Then, the adjacent character richness of the candidate emoji combination can be calculated according to the following formula (3):

[0087]

[0088] Where R(C) represents the richness of adjacent characters of the candidate emoji combination, E1 represents the richness of the first adjacent characters of the candidate emoji combination, and E2 represents the richness of the first adjacent characters of the candidate emoji combination.

[0089] In this way, the richness of adjacent characters of the candidate emoji combination can be obtained through the above formula. The greater the richness of adjacent characters, the greater the probability that the candidate emoji combination is the target emoji combination.

[0090] Furthermore, the dependencies between multiple emojis in the candidate emoji combination can be obtained through the following steps:

[0091] First, obtain the first probability of the candidate emoji combination appearing in multiple target texts.

[0092] Secondly, obtain the second probability of each emoji in the candidate emoji combination appearing in multiple target texts.

[0093] Finally, the dependency of the candidate emoji combination is calculated based on the first probability, the second probability, and the number of emojis in the candidate emoji combination.

[0094] For example, the above candidate emoji combination C includes a emojis: t1, t2, ..., t a Then the dependency of the candidate emoji combination can be calculated according to the following formula (4):

[0095]

[0096] Where AMI(C) represents the dependency of the candidate emoji combination, P(C) represents the probability of the candidate emoji combination C appearing in multiple target texts, a represents the number of emojis in the candidate emoji combination, and t represents the probability of the candidate emoji combination C appearing in multiple target texts. h This indicates that the h-th expression matches, where h ranges from 1 to a, P(t) h ) indicates that the h-th expression matches t. hThe probability of appearing in multiple target texts Represents the transition from P(t1) to P(t). a The product operation.

[0097] In this way, the dependency of the candidate emoji combination can be obtained through the above formula. The greater the dependency, the greater the probability that the candidate emoji combination is the target emoji combination.

[0098] In another embodiment of this disclosure, the step S103 above, which determines the target emoji combination from multiple candidate emoji combinations based on the richness and dependency of adjacent characters in each candidate emoji combination, may further include the following steps:

[0099] First, for each candidate emoji combination, the combination score of the candidate emoji combination is calculated based on the richness of the adjacent characters and the dependency of the candidate emoji combination.

[0100] For example, the combination score of the candidate emoji combination can be calculated according to the following formula (5):

[0101] S=R(C)+AMI(C) (5)

[0102] Where S represents the combination score of the candidate emoji combination, R(C) represents the adjacent character richness of the candidate emoji combination, and AMI(C) represents the dependency of the candidate emoji combination.

[0103] Optionally, in this step, the combination score of the candidate emoji combination can also be calculated according to the following formula (6):

[0104] S=D1*R(C)+D2*AMI(C) (6)

[0105] Where S represents the combination score of the candidate emoji combination, R(C) represents the richness of adjacent characters of the candidate emoji combination, AMI(C) represents the dependency of the candidate emoji combination, D1 represents the preset richness coefficient, and D2 represents the dependency coefficient.

[0106] The preset richness coefficient and the preset dependency coefficient can be set based on empirical values. The ratio of the richness and dependency of adjacent characters in the candidate emoji combination can be adjusted according to the preset richness coefficient and the preset dependency coefficient, so as to obtain a more accurate combination score.

[0107] Secondly, based on the combination, multiple candidate emoji combinations are sorted.

[0108] Finally, the top-ranked candidate emoji combinations in the sorting results are selected as the target emoji combination.

[0109] For example, this sorting can be based on the size of the combined score, with larger combined scores appearing earlier in the sorting list and smaller combined scores appearing later in the sorting list.

[0110] In this way, by sorting multiple candidate emoji combinations according to the richness and dependency of adjacent characters of each candidate emoji combination, the target emoji combination can be obtained efficiently.

[0111] Figure 2 This is a block diagram illustrating an apparatus for acquiring combinations of emojis according to an exemplary embodiment, such as... Figure 2 As shown, the device includes:

[0112] The candidate emoji combination acquisition module 201 is configured to acquire multiple candidate emoji combinations from multiple target texts, wherein the candidate emoji combination includes multiple emojis;

[0113] The candidate emoji combination analysis module 202 is configured to, for each candidate emoji combination, obtain one or more adjacent characters from multiple target texts that are adjacent to the candidate emoji combination, and obtain the adjacent character richness of the candidate emoji combination based on the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination, and obtain the dependency between the multiple emojis of the candidate emoji combination based on the probability of the multiple emojis of the candidate emoji combination appearing individually in multiple target texts and the probability of the candidate emoji combination appearing in multiple target texts; wherein, the one or more adjacent characters are one or more non-repeating characters obtained after deduplicating the characters adjacent to the candidate emoji combination in multiple target texts.

[0114] The target emoji combination determination module 203 is configured to determine a target emoji combination from multiple candidate emoji combinations based on the richness of adjacent characters and the dependency of each candidate emoji combination.

[0115] Optionally, the adjacent characters include a first adjacent character and a second adjacent character, wherein the first adjacent character is the character adjacent to the first side of the candidate emoji combination, and the second adjacent character is the character adjacent to the second side of the candidate emoji combination; the candidate emoji combination analysis module 202 is configured to:

[0116] Based on the number of the first adjacent characters and the first adjacent probability of each first adjacent character with the candidate emoji combination, the richness of the first adjacent characters of the candidate emoji combination is calculated.

[0117] Based on the number of the second adjacent characters and the second adjacent probability of each second adjacent character with the candidate emoji combination, the richness of the second adjacent characters of the candidate emoji combination is calculated.

[0118] The richness of adjacent characters is calculated based on the richness of the first adjacent character and the richness of the second adjacent character.

[0119] Optionally, the candidate emoji combination analysis module 202 is configured as follows:

[0120] Obtain the first probability of the candidate emoji combination appearing in multiple instances of the target text;

[0121] Obtain the second probability of each emoji in the candidate emoji combination appearing in multiple instances of the target text;

[0122] The dependency of the candidate emoji combination is calculated based on the first probability, the second probability, and the number of emojis in the candidate emoji combination.

[0123] Optionally, the target emoji combination determination module 203 is configured to

[0124] For each candidate emoji combination, the combination score of the candidate emoji combination is calculated based on the richness of the adjacent characters and the dependency of the candidate emoji combination.

[0125] Based on this combination, sort multiple candidate emoji combinations;

[0126] The first few candidate emoji combinations in the sorting results are selected as the target emoji combination.

[0127] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0128] In summary, this technical solution extracts multiple candidate emoji combinations from multiple target texts. Each candidate emoji combination includes multiple emojis. For each candidate emoji combination, one or more adjacent characters are extracted from the target text. Based on the number of adjacent characters and the probability of each adjacent character being adjacent to the candidate emoji combination, the richness of adjacent characters in the candidate emoji combination is obtained. Furthermore, based on the probability of each emoji in the candidate emoji combination appearing individually in the target text and the probability of the candidate emoji combination appearing in the target text, the dependency between the emojis in the candidate emoji combination is obtained. Finally, based on the richness and dependency of adjacent characters for each candidate emoji combination, the target emoji combination is determined from the multiple candidate emoji combinations. Thus, through unsupervised mining, target emoji combinations can be efficiently extracted from a large amount of target text based on the richness and dependency of adjacent characters.

[0129] Figure 3 This is a block diagram illustrating an electronic device 300 according to an exemplary embodiment. For example, the electronic device 300 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, router, etc.

[0130] Reference Figure 3 The electronic device 300 may include one or more of the following components: processing component 302, memory 304, power component 306, multimedia component 308, audio component 310, input / output (I / O) interface 312, sensor component 314, and communication component 316.

[0131] Processing component 302 typically controls the overall operation of electronic device 300, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the method for obtaining emoji combinations described above. Furthermore, processing component 302 may include one or more modules to facilitate interaction between processing component 302 and other components. For example, processing component 302 may include a multimedia module to facilitate interaction between multimedia component 308 and processing component 302.

[0132] Memory 304 is configured to store various types of data to support the operation of electronic device 300. Examples of such data include instructions for any application or method operating on electronic device 300, contact data, phonebook data, messages, pictures, videos, etc. Memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0133] Power component 306 provides power to various components of electronic device 300. Power component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 300.

[0134] Multimedia component 308 includes a screen that provides an output interface between the electronic device 300 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 touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 308 includes a front-facing camera and / or a rear-facing camera. When the electronic device 300 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0135] Audio component 310 is configured to output and / or input audio signals. For example, audio component 310 includes a microphone (MIC) configured to receive external audio signals when electronic device 300 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 304 or transmitted via communication component 316. In some embodiments, audio component 310 also includes a speaker for outputting audio signals.

[0136] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0137] Sensor assembly 314 includes one or more sensors for providing state assessments of various aspects of electronic device 300. For example, sensor assembly 314 can detect the on / off state of electronic device 300, the relative positioning of components such as the display and keypad of electronic device 300, changes in position of electronic device 300 or a component of electronic device 300, the presence or absence of user contact with electronic device 300, orientation or acceleration / deceleration of electronic device 300, and temperature changes of electronic device 300. Sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 314 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0138] Communication component 316 is configured to facilitate wired or wireless communication between electronic device 300 and other devices. Electronic device 300 can access wireless networks based on communication standards, such as Wi-Fi, 2G, 3G, 4G, 5G, NB-IoT, eMTC, or other 6G networks, or combinations thereof. In one exemplary embodiment, communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0139] In an exemplary embodiment, the electronic device 300 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-described method for obtaining combinations of emojis.

[0140] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, which can be executed by a processor 320 of an electronic device 300 to complete the method for obtaining the emoji combination described above. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0141] In another exemplary embodiment, a computer program product is also provided, comprising a computer program executable by a programmable device, the computer program having a code portion for performing the method of obtaining the above-described combination of emojis when executed by the programmable device.

[0142] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0143] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for obtaining combinations of emojis, characterized in that, The method includes: Multiple candidate emoji combinations are obtained from multiple target texts, wherein the candidate emoji combinations include multiple emojis; For each candidate emoji combination, one or more adjacent characters are obtained from multiple target texts. Based on the number of the one or more adjacent characters and the probability of each adjacent character being adjacent to the candidate emoji combination, the richness of adjacent characters for the candidate emoji combination is obtained. Based on the probability of multiple emojis in the candidate emoji combination appearing individually in multiple target texts and the probability of the candidate emoji combination appearing in multiple target texts, the dependency between the multiple emojis in the candidate emoji combination is obtained. The one or more adjacent characters are one or more non-repeating characters obtained by deduplicating the characters adjacent to the candidate emoji combination in multiple target texts. The target emoji combination is determined from the plurality of candidate emoji combinations based on the richness of adjacent characters and the dependency of each candidate emoji combination.

2. The method according to claim 1, characterized in that, The adjacent characters include a first adjacent character and a second adjacent character. The first adjacent character is the character adjacent to the first side of the candidate emoji combination, and the second adjacent character is the character adjacent to the second side of the candidate emoji combination. The step of obtaining the adjacent character richness of the candidate emoji combination based on the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination includes: Based on the number of the first adjacent characters and the first adjacent probability of each first adjacent character with the candidate emoji combination, the richness of the first adjacent characters of the candidate emoji combination is calculated. The richness of the second adjacent characters of the candidate emoji combination is calculated based on the number of the second adjacent characters and the second adjacent probability of each second adjacent character with the candidate emoji combination. The adjacent character richness is calculated based on the first adjacent character richness and the second adjacent character richness.

3. The method according to claim 1, characterized in that, The step of obtaining the dependency between the multiple emojis in the candidate emoji combination based on the probability of each emoji appearing individually in multiple target texts and the probability of the candidate emoji combination appearing in multiple target texts includes: Obtain the first probability of the candidate emoji combination appearing in multiple target texts; Obtain the second probability of each emoji in the candidate emoji combination appearing in multiple target texts; The dependency of the candidate emoji combination is calculated based on the first probability, the second probability, and the number of emojis in the candidate emoji combination.

4. The method according to claim 1, characterized in that, The step of determining the target emoji combination from multiple candidate emoji combinations based on the adjacent character richness and the dependency of each candidate emoji combination includes: For each candidate emoji combination, the combination score of the candidate emoji combination is calculated based on the richness of adjacent characters and the dependency of the candidate emoji combination. Sort the multiple candidate emoji combinations according to the combination score; The first few candidate emojis in the sorting results are combined to form the target emoji combination.

5. A device for acquiring combinations of emojis, characterized in that, The device includes: The candidate emoji combination acquisition module is configured to acquire multiple candidate emoji combinations from multiple target texts, wherein the candidate emoji combinations include multiple emojis; The candidate emoji combination analysis module is configured to, for each candidate emoji combination, obtain one or more adjacent characters from multiple target texts that are adjacent to the candidate emoji combination, and obtain the adjacent character richness of the candidate emoji combination based on the number of the one or more adjacent characters and the adjacent probability of each adjacent character with the candidate emoji combination, and obtain the dependency between the multiple emojis of the candidate emoji combination based on the probability of the multiple emojis of the candidate emoji combination appearing individually in multiple target texts and the probability of the candidate emoji combination appearing in multiple target texts; wherein, the one or more adjacent characters are one or more non-repeating characters obtained after deduplicating the characters adjacent to the candidate emoji combination in multiple target texts; The target emoji combination determination module is configured to determine a target emoji combination from a plurality of candidate emoji combinations based on the adjacent character richness and the dependency of each candidate emoji combination.

6. The apparatus according to claim 5, characterized in that, The adjacent characters include a first adjacent character and a second adjacent character. The first adjacent character is the character adjacent to the first side of the candidate emoji combination, and the second adjacent character is the character adjacent to the second side of the candidate emoji combination. The candidate emoji combination analysis module is configured as follows: Based on the number of the first adjacent characters and the first adjacent probability of each first adjacent character with the candidate emoji combination, the richness of the first adjacent characters of the candidate emoji combination is calculated. The richness of the second adjacent characters of the candidate emoji combination is calculated based on the number of the second adjacent characters and the second adjacent probability of each second adjacent character with the candidate emoji combination. The adjacent character richness is calculated based on the first adjacent character richness and the second adjacent character richness.

7. The apparatus according to claim 5, characterized in that, The candidate emoji combination analysis module is configured as follows: Obtain the first probability of the candidate emoji combination appearing in multiple target texts; Obtain the second probability of each emoji in the candidate emoji combination appearing in multiple target texts; The dependency of the candidate emoji combination is calculated based on the first probability, the second probability, and the number of emojis in the candidate emoji combination.

8. The apparatus according to claim 5, characterized in that, The target emoji combination determination module is configured as follows: For each candidate emoji combination, the combination score of the candidate emoji combination is calculated based on the richness of adjacent characters and the dependency of the candidate emoji combination. Sort the multiple candidate emoji combinations according to the combination score; The first few candidate emojis in the sorting results are combined to form the target emoji combination.

9. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processing device, the program implements the steps of the method according to any one of claims 1 to 4.

Images