A data processing method, a data processing device and a data processing device

Through generalization processing and matching of multivariate relational data, the low hit rate problem caused by uneven distribution of existing binary libraries in corpus is solved, the hit rate of associative candidates is improved, and the intelligence and coverage of the input method are enhanced.

CN112306252BActive Publication Date: 2024-11-26BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN201910696231.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-07-30
Publication Date
2024-11-26
Estimated Expiration
2040-05-23

AI Technical Summary

Technical Problem

In actual applications, the existing binary library has a low hit rate of associative candidates due to uneven corpus distribution, and cannot effectively match the user's input content.

Method used

Through generalization processing technology, the generalization processing results above are determined, and the generalization elements in the multivariate relationship data are used to improve the matching rate and hit rate, thereby improving the hit rate of the first association candidate.

Benefits of technology

通过泛化处理和多元关系数据的匹配,提高了联想候选的命中率,增强了输入法的智能性和覆盖率,提高了用户输入的效率。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112306252B_ABST
    Figure CN112306252B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention provides a data processing method, device and device for data processing. The method specifically includes: determining the generalization processing result corresponding to the above text; determining the first association candidate corresponding to the above text according to the generalization processing result and multivariate relationship data; wherein the multivariate relationship data includes: the relationship between at least two elements, at least one of the at least two elements has been generalized; outputting the first association candidate. The embodiment of the present invention can improve the hit rate of the first association candidate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of input technologies, and in particular, to a data processing method, an apparatus, and an apparatus for data processing. Background Art

[0002] As a bridge for a computer system to communicate with a user or other devices, a device is one of the main apparatuses for information interaction between the user and the computer system, and it can facilitate the user to input information in various scenarios. For example, a user can input keywords in a search engine to search for web pages, input text in an instant messaging APP (Application) to communicate with other users, input text in a document APP to edit a document, and so on.

[0003] The input method association function is an extended function of an input method program. Its appearance reduces the number of times of active input by the user and the number of key presses, and increases the intelligence of the input method. The implementation process of this input method is to first obtain the previous text input by the user, and query a preset thesaurus such as a system binary thesaurus according to the previous text to obtain association candidates. For example, if the previous text is "Believe in Brother Chun", the association candidate can be "Gain eternal life". For example, if the previous text is "Africans come to Beijing to escape the heat", the association candidate can be "As a result, they got heatstroke".

[0004] The binary library can be used to record the binary relationship between two elements, and the elements can include: words, phrases, short sentences, etc. The current binary library can be obtained by training based on corpus. In actual applications, factors such as uneven distribution of the corpus easily lead to low coverage and hit rate of the binary library, and further result in a low hit rate of the association candidates. For example, if the binary relationship 1 between "Believe in Brother Chun" and "Gain eternal life" is recorded in the binary library, when the previous text 1 is "Believe in Brother He", the previous text 1 will not hit the binary relationship 1, and thus the corresponding association candidate cannot be obtained. Another example is that if the binary relationship 2 between "Africans come to Beijing to escape the heat" and "As a result, they got heatstroke" is recorded in the binary library, when the previous text 2 is "Africans come to Xi'an to escape the heat", the previous text 2 will not hit the binary relationship 2, and thus the corresponding association candidate cannot be obtained. Summary of the Invention

[0005] Embodiments of the present invention provide a data processing method, an apparatus, and an apparatus for data processing, which can improve the hit rate of the first association candidate.

[0006] To solve the above problems, embodiments of the present invention disclose a data processing method, including:

[0007] Determine the generalization processing result corresponding to the previous text;

[0008] Determining the first association candidate corresponding to the above context according to the generalization processing result and multi-relation data; wherein the multi-relation data includes: a relationship between at least two elements, at least one of the at least two elements being generalized;

[0009] The first association candidate is output.

[0010] On the other hand, an embodiment of the present invention discloses a data processing device, including:

[0011] A generalization processing result determination module, used to determine the generalization processing result corresponding to the above text;

[0012] A first association candidate determination module is configured to determine a first association candidate corresponding to the above text according to the generalization processing result and multivariate relationship data; wherein the multivariate relationship data includes: a relationship between at least two elements, at least one of the at least two elements being generalized; and

[0013] The first association candidate output module is used to output the first association candidate.

[0014] In another aspect, an embodiment of the present invention discloses a device for data processing, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations:

[0015] Determine the generalization processing result corresponding to the above text;

[0016] Determining the first association candidate corresponding to the above context according to the generalization processing result and multi-relation data; wherein the multi-relation data includes: a relationship between at least two elements, at least one of the at least two elements being generalized;

[0017] The first association candidate is output.

[0018] On the other hand, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the device to perform one or more of the data processing methods described above.

[0019] The embodiments of the present invention include the following advantages:

[0020] The embodiment of the present invention determines the first association candidate corresponding to the above text based on the generalization processing result corresponding to the above text and the multi-relation data; since the generalization processing result corresponding to the above text is obtained after generalization processing of the above text, it can include higher-level concepts; and at least one element in the multi-relation data has also been generalized, so it can include higher-level concepts; therefore, the embodiment of the present invention can improve the matching rate and hit rate between the generalization processing result and the multi-relation data, and thus can improve the hit rate of the first association candidate. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0022] Figure 1 It is a schematic diagram of an application environment of a data processing method according to an embodiment of the present invention;

[0023] Figure 2 is a flow chart of steps of a data processing method embodiment 1 of the present invention;

[0024] Figure 3 is a flow chart of steps of a second embodiment of a data processing method of the present invention;

[0025] Figure 4 is a flow chart of steps of a data processing method embodiment 3 of the present invention;

[0026] Figure 5 is a flow chart of the steps of a fourth embodiment of a data processing method of the present invention;

[0027] Figure 6 is a structural block diagram of an embodiment of a data processing device of the present invention;

[0028] Figure 7 is a block diagram of an apparatus 800 for data processing according to the present invention; and

[0029] Figure 8 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] An embodiment of the present invention provides a data processing scheme, which can determine the generalization processing result corresponding to the above text; determine the first association candidate corresponding to the above text based on the generalization processing result and multi-relationship data; wherein the multi-relationship data may include: the relationship between at least two elements, at least one of the above at least two elements has been generalized; and output the first association candidate.

[0032] In an embodiment of the present invention, the context may refer to the part before the input cursor. According to one embodiment, the context may include: the most recent or most recent on-screen content. According to another embodiment, the context may include: the communication content sent by the communication counterpart in a communication scenario. For example, in an instant messaging scenario, after user A receives the communication content "Africans come to Xi'an to escape the summer heat" sent by user B, he clicks on the input box to input, and an input cursor may appear in the input box. Since the communication content is located before the input cursor in the communication window, the communication content may be used as the context. It can be understood that the embodiments of the present invention are not limited to the specific context.

[0033] Generalization can refer to expanding the specific and individual into the general. Data usually contains detailed information of the original concept layer, so the generalization processing of the embodiment of the present invention can abstract data from a lower concept layer to a higher concept layer, and replace the lower-level concepts with higher-level concepts. For example, "place" replaces "Xi'an", or province replaces prefecture-level concepts, etc.

[0034] The embodiment of the present invention determines the first association candidate corresponding to the above text based on the generalization processing result corresponding to the above text and the multi-relation data; since the generalization processing result corresponding to the above text is obtained after generalization processing of the above text, it can include higher-level concepts; and at least one element in the multi-relation data has also been generalized, so it can include higher-level concepts; therefore, the embodiment of the present invention can improve the matching rate and hit rate between the generalization processing result and the multi-relation data, and thus can improve the hit rate of the first association candidate.

[0035] Taking the above text "Africans come to Xi'an to escape the heat" as an example, the embodiment of the present invention can determine the generalization result corresponding to "Africans come to Xi'an to escape the heat": "Africans come to a place to escape the heat"; and, the relationship between "Africans come to a place to escape the heat" and "the result is heatstroke" can be recorded in the multi - relationship data of the embodiment of the present invention; therefore, the embodiment of the present invention can determine the first association candidate corresponding to "Africans come to Xi'an to escape the heat": "the result is heatstroke".

[0036] Taking the above text "Believe in Brother He" as an example, the embodiment of the present invention can determine the generalization result corresponding to "Believe in Brother He": "Believe in a person's name"; and, the relationship between "Believe in a person's name" and "gain eternal life" can be recorded in the multi - relationship data of the embodiment of the present invention; therefore, the embodiment of the present invention can determine the first association candidate corresponding to "Believe in Brother He": "gain eternal life".

[0037] Taking the above text "If you want to know the taste of a pear" as an example, the embodiment of the present invention can determine the generalization result corresponding to "If you want to know the taste of a pear": "If you want to know the taste of a fruit"; and, the relationship between "If you want to know the taste of a fruit" and "you have to taste it yourself" can be recorded in the multi - relationship data of the embodiment of the present invention; therefore, the embodiment of the present invention can determine the first association candidate corresponding to "If you want to know the taste of a pear": "you have to taste it yourself".

[0038] The data processing method provided by the embodiment of the present invention can be applied to input method programs for various input methods such as keyboard symbols, voice, and handwriting, that is, users can input text through an encoded string (i.e., the input string in the embodiment of the present invention). In the field of input methods, for input method programs for languages such as Chinese, Japanese, Korean, or other languages, usually, the input string input by the user can be converted into candidate items in the corresponding language. The following mainly takes Chinese as an example for illustration, and other languages such as Japanese and Korean can be referred to each other. It can be understood that the Chinese input method can include but is not limited to full - spelling, simple - spelling, stroke - input,五笔, etc., and the embodiment of the present invention does not limit the specific input method program corresponding to a certain language.

[0039] The data processing method provided by the embodiment of the present invention can be applied to Figure 1 the application environment shown, such as Figure 1 shown, the client 100 and the server 200 are located in a wired or wireless network. Through this wired or wireless network, the client 100 and the server 200 perform data interaction.

[0040] Optionally, the client 100 may be run on a terminal, which specifically includes but is not limited to: a smart phone, a tablet computer, an e-book reader, an MP3 (Moving Picture Experts Group Audio Layer III) player, an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a car computer, a desktop computer, a set-top box, a smart TV, a wearable device, etc. The client 100 may correspond to a website or an APP (Application).

[0041] In actual applications, for the input method of keyboard symbols, the user can input the above input string through a physical keyboard or a virtual keyboard. For example, for a terminal with a touch screen, a virtual keyboard can be set in the input interface to input the input string by triggering the virtual keys included in the above virtual keyboard. Optionally, examples of the above virtual keyboard may include: a 9-key keyboard and a 26-key keyboard. In addition, it can be understood that in addition to the virtual keys corresponding to letters, the above input interface can also be provided with symbol keys, number keys, such as function keys for switching between Chinese and English, or toolbar keys, etc. It can be understood that the embodiment of the present invention does not limit the specific keys included in the input interface.

[0042] According to some embodiments, the input string may include, but is not limited to, a key symbol or a combination of multiple key symbols input by a user through a key. The key symbol may specifically include: pinyin, strokes, kana, and the like.

[0043] In an embodiment of the present invention, a candidate may be used to represent one or more characters provided by an input method program to be selected by a user. The candidate may correspond to the above, or the candidate may correspond to an input string, or the candidate may correspond to an input string and the above. The candidate may be characters in languages ​​such as Chinese characters, English characters, and Japanese characters, and the candidate may also be a combination of symbols in the form of emoticons, pictures, and the like. The emoticons include, but are not limited to, pictures composed of lines, symbols, and words. For example, examples of the emoticons may include: “:P”, “:-o”, “:-)”, and the like.

[0044] Multivariate relational data may include binary and more than binary relational data. A binary relation, also known as a 2-gram, is used to represent the probability of two elements appearing one after another. In the field of input methods, the elements here may include at least one of: vocabulary, phrases, short sentences, letters, numbers, and symbols. In an embodiment of the present invention, the binary may mainly include binary relations of vocabulary, and other types of binary relations may refer to each other. Relations of more than two elements are used to represent the probability of more than two elements appearing one after another.

[0045] For vocabulary, its binary relationship data is mainly used to reflect the probability of two words being used adjacently. On the one hand, the vocabulary may include language characters composed of letters, which may be words, phrases, and short phrases composed of letters printed on a keyboard, and may be specifically applicable to English, French, German, etc. On the other hand, the vocabulary may also include character sequences corresponding to text languages ​​composed of pinyin and / or strokes. Here, the character sequences corresponding to text languages ​​composed of pinyin and / or strokes may include words corresponding to pinyin, words corresponding to strokes, etc., and may be specifically applicable to Chinese, Japanese, Korean, etc.

[0046] In an optional embodiment of the present invention, multivariate relational data can be represented by a data model. The types of data models may include, but are not limited to, language models, neural network models, etc. The above data model can provide P(any element|previous context, ...), that is, the probability of any element under certain previous context conditions. Based on this probability, the association candidate corresponding to the previous context can be determined. Among them, the corpus used by the data model may include: corpus under the above context conditions, and the above corpus includes, but is not limited to: Internet corpus, user's voice chat corpus, user's input corpus, etc.

[0047] Mathematical model is a scientific or engineering model constructed by mathematical logic methods and mathematical language. Mathematical model is a mathematical structure that is expressed in general or approximate terms using mathematical language with reference to the characteristics or quantitative dependencies of a certain system of things. This mathematical structure is a relational structure depicted with the help of mathematical symbols. Mathematical model can be one or a group of algebraic equations, differential equations, difference equations, integral equations or statistical equations and their combinations, which quantitatively or qualitatively describe the mutual relationship or causal relationship between the variables of the system. In addition to mathematical models described by equations, there are also models described by other mathematical tools, such as algebra, geometry, topology, mathematical logic, etc. Among them, mathematical models describe the behavior and characteristics of the system rather than the actual structure of the system. Among them, machine learning, deep learning methods and other methods can be used to train mathematical models. Machine learning methods may include: linear regression, decision tree, random forest, etc. Deep learning methods may include: convolutional neural networks (CNN), long short-term memory networks (LSTM), gated recurrent units (GRU), etc.

[0048] Optionally, the conditions of the data model may further include: input environment characteristics. In this case, the data model may provide P (any element|previous text, input environment characteristics, ...).

[0049] In the embodiment of the present invention, the input environment feature can be used to characterize the environment information of the terminal when the user inputs. The input environment feature can reflect the user's input intention to a certain extent. Therefore, by establishing a connection between the input environment feature and the user's input intention, the user's input intention can be indirectly identified, thereby improving the user's input efficiency.

[0050] In practical applications, the input environment features may include various types of features. Optionally, the input environment features may include at least one of time environment features, location environment features, climate environment features, application environment features, and page environment features.

[0051] Even for the same terminal, the environment information is likely to change, and the time environment feature is a typical example. Therefore, the input environment feature of the embodiment of the present invention can be real-time, and the input environment feature corresponding to the input string can be obtained in real time during the input process.

[0052] For an input string, its receiving time can be used as the corresponding time environment feature.

[0053] The location information obtained according to its IP (Internet Protocol) address, the GPS (Global Positioning System) of the terminal or the mobile communication network can be used as the corresponding location environment feature.

[0054] As a host program, the input method program can be hosted in any host program and can be called by the host program to implement input in the host program. For example, a user can type an input string in the host program and select a candidate item corresponding to the input string. In the embodiment of the present invention, the application environment feature corresponding to the input string can be information of the host program corresponding to the input method program.

[0055] Optionally, the application environment characteristics corresponding to the input string can be determined based on the identification characteristics of the current object being served by the input method program. For example, when the input method program is running, it calls GetModuleFilename to find the program path name "C:ProgramFilesMicrosoftOfficeOFFICE11WINWORD.EXE", and the corresponding application environment characteristics can be determined to be "WinWord.exe", that is, the input string is entered in "word". Of course, the embodiment of the present invention does not limit the specific method for obtaining the application environment characteristics corresponding to the input string.

[0056] In an embodiment of the present invention, the application environment feature may include: an application identifier and / or an application category. For example, "word" is an application identifier, and the application category corresponding to "word" is an office category, etc. It can be understood that those skilled in the art can classify applications into corresponding application categories according to actual application requirements. For example, examples of application categories may include but are not limited to: instant messaging category, document category, search category, web page category, shopping category, travel category, etc.

[0057] Page environment features can be used to characterize the page environment provided by an application or website. Optionally, the above-mentioned page environment may include but is not limited to: instant messaging page environment, document page environment, email page environment, password input page environment, game page environment, search page environment, travel page environment, shopping page environment, social page environment, film and television page environment, reading page environment, etc.

[0058] Of course, in addition to time environment features, location environment features, application environment features and page environment features, the input environment features of the embodiment of the present invention may also include other environment features, for example, physical environment features such as air pressure, altitude, temperature, humidity, etc. It can be understood that the embodiment of the present invention does not limit the specific input environment features.

[0059] Method Example 1

[0060] Reference Figure 2 , shows a flow chart of the steps of a data processing method embodiment 1 of the present invention, which may specifically include the following steps:

[0061] Step 201: generalize the left element in the multivariate relational data to obtain the first element;

[0062] Step 202: Obtain the relationship between the first element and the second element according to the first element and the right element in the multi-element relationship data.

[0063] Figure 2 At least one step of the illustrated embodiment may be executed by a server or a client. Of course, the embodiment of the present invention does not limit the specific execution subject of each step.

[0064] The binary relation data may include: a left element and a right element. The left element may be located on the left side of the right element, that is, the left element may be located in front of the right element.

[0065] Figure 2 The illustrated embodiment may be used to perform generalization processing on the left element in multi-element relational data to obtain the relationship between the first element and the second element.

[0066] Multivariate relational data can be obtained by training the corpus. In practical applications, factors such as uneven distribution of the corpus can easily lead to a low coverage rate of multivariate relational data. For example, the corpus may include: "Believe in Brother Chun and you will have eternal life", "Africans came to Beijing to escape the summer heat and got heatstroke", "If you want to know the taste of apples, you have to taste them yourself", etc. The multivariate relational data obtained based on the above corpus will not cover "Believe in Brother He", "Africans came to Xi'an to escape the summer heat", "If you want to know the taste of pears", etc.

[0067] In order to improve the coverage of multivariate relational data, the embodiment of the present invention generalizes at least one element in the multivariate relational data. The element in the multivariate relation can be used to represent an element in the multivariate relation, and optionally an element can be represented by an independent field.

[0068] Figure 2 The method embodiment shown can generalize the left element in the multivariate relational data to obtain the first element, and then obtain the relationship between the first element and the second element; since the first element in the multivariate relational data has been generalized, the coverage and hit rate of the multivariate relational data can be improved.

[0069] In the embodiment of the present invention, the left element and the right element in the multi-element relation data may be determined according to the order in which the elements appear in the language.

[0070] The embodiment of the present invention can provide the following technical solution for generalizing the left element in multivariate relational data:

[0071] Technical solution A1,

[0072] In technical solution A1, the generalization processing of the left element in the multi-relation data may specifically include: generalization processing of the left element in the multi-relation data according to the mapping relationship between words and word categories.

[0073] The word category can be used to characterize the category of the word. Optionally, the mapping relationship between the word and the word category can be saved through a semantic dictionary. The following mapping relationships can be saved in the semantic dictionary: apple-fruit, Beijing-city, sunny-weather, happy-mood, etc. It can be understood that the embodiment of the present invention does not limit the specific mapping relationship between the word and the word category.

[0074] The process of generalizing the left element in the multi-relation data may include: matching the left element in the multi-relation data with the word in the mapping relationship, and if the match is successful, replacing the left element with the corresponding word category.

[0075] It should be noted that the left-hand element may include: one target word that matches the mapping relationship; or the left-hand element may include: multiple target words that match the mapping relationship. In this case, generalization processing can be performed on the multiple target words respectively.

[0076] For example, the left-hand element includes: target word 1 and target word 2, and the corresponding generalization processing methods may include: generalization processing only for target word 1; generalization processing only for target word 2; or generalization processing for target word 1 and target word 2 at the same time; therefore, the embodiment of the present invention can obtain multiple generalization processing results for one left-hand element.

[0077] Therefore, the embodiment of the present invention may perform generalization processing on a single target word in the left-gram, or may perform generalization processing on multiple target words in the left-gram, thereby obtaining multiple generalization processing results.

[0078] Technical solution A2,

[0079] In technical solution A2, the generalization processing of the left-gram in the multi-relation data may specifically include: identifying at least one entity word in the left-gram; replacing at least one entity word in the left-gram with a corresponding entity category word.

[0080] In the embodiment of the present invention, an entity is a specific thing or concept. Entities are generally divided into types, such as person entities, movie entities, animal entities, historical entities, etc. The same entity can correspond to multiple entity instances, and an entity instance can be a descriptive page (content) of an entity on the Internet (or other media), such as an encyclopedia page that contains an entity instance corresponding to the entity.

[0081] Optionally, entities may include: named entities, which may refer to names of people, institutions, places, and all other entities identified by names. More extensive named entities may also include: book titles, song titles, film and television drama titles, product names, brand names, numbers, dates, currencies, addresses, and so on.

[0082] Optionally, the entity category may include at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothing, food, medicines, vehicles, furniture, musical instruments, electrical appliances, and natural phenomena.

[0083] In one embodiment of the present invention, a NER (Named Entity Recognition) method may be used to determine entities in the text content.

[0084] According to one embodiment, the NER method may include: a thesaurus-based method. The thesaurus-based method can construct an entity library for high-frequency words based on the frequency of occurrence of phrases, and directly identify the words that can be retrieved in the entity library as entities. Among them, a phrase can refer to a combination of two or more words. In practical applications, entity-related data can be captured from the Internet, and the entity-related data can be analyzed to obtain corresponding entity words, and the entity words can be stored in the entity library. The embodiment of the present invention does not limit the specific entity words and their acquisition methods.

[0085] According to another embodiment, the NER method may include: a rule-based method. The rule-based method may mark the phrases in the request that meet the corresponding rules as entities according to the composition rules of the phrases.

[0086] According to another embodiment, the NER method may include: a method based on statistical learning. The method based on statistical learning regards named entity recognition as a classification problem, and adopts classification methods such as SVM (Support Vector Machine) and Bayesian; or, regards named entity recognition as a sequence labeling problem, and adopts sequence labeling models such as HMM (Hidden Markov Model), Maximum Entropy Model, CRF (Conditional Random Field, Conditional Random Field Algorithm), LSTM (Long Short-Term Memory Network, Long Short-Term Memory) model.

[0087] It should be noted that the left-hand element may include: one entity word; or, the left-hand element may include: multiple entity words. In this case, generalization processing may be performed on the multiple entity words respectively.

[0088] For example, the left element includes: entity word 1 and entity word 2, then the corresponding generalization processing methods may include: generalization processing only for entity word 1; generalization processing only for entity word 2; or generalization processing for entity word 1 and entity word 2 at the same time; therefore, the embodiment of the present invention can obtain multiple generalization processing results for one left element.

[0089] Therefore, the embodiment of the present invention may perform generalization processing on a single entity word in the left-gram, or may perform generalization processing on multiple entity words in the left-gram, thereby obtaining multiple generalization processing results.

[0090] It can be understood that identifying at least one entity word in the left-hand element is only an optional embodiment. In fact, adjectives, verbs, etc. in the left-hand element can also be identified.

[0091] In step 202, the right element in the multi-element relation data may be used as the second element, thereby obtaining the relationship between the first element and the second element and saving it.

[0092] In summary, the data processing method of the embodiment of the present invention generalizes the left element in the multivariate relational data to obtain the first element, and then obtains the relationship between the first element and the second element; since the first element in the multivariate relational data has been generalized, the coverage and hit rate of the multivariate relational data can be improved.

[0093] It can be understood that the above generalization of the left element in the multivariate relational data to obtain the first element is only an optional embodiment. In fact, the embodiment of the present invention can also generalize the right element in the multivariate relational data to obtain the second element, and then obtain the relationship between the first element and the second element.

[0094] In actual applications, there may be a situation where the user remembers the second half of an expression but forgets the first half. In this case, the user can input the second half of the expression. The embodiment of the present invention can automatically provide the first half of the expression through the second element after generalization processing, and can improve the hit rate of the first association candidate.

[0095] It can be understood that the relationship between the first element and the second element mentioned above is only an example. In fact, the multivariate relational data of the embodiment of the present invention can represent the mapping relationship between more than two elements. In this case, at least one of the more than two elements can be generalized to improve the coverage and hit rate of the multivariate relational data.

[0096] Method Example 2

[0097] Reference Figure 3 , shows a flow chart of the steps of a data processing method embodiment 2 of the present invention, which may specifically include the following steps:

[0098] Step 301, determine the generalization processing result corresponding to the above text;

[0099] Step 302: determining the first association candidate corresponding to the above text according to the generalization processing result and the multivariate relationship data; wherein the multivariate relationship data may include: a relationship between at least two elements, at least one of the at least two elements being generalized;

[0100] Step 303: output the first association candidate.

[0101] Figure 3 At least one step of the illustrated embodiment may be executed by the server and / or the client. Of course, the embodiment of the present invention does not limit the specific execution subject of each step.

[0102] In step 301, the client may obtain the above text and determine the generalization processing result corresponding to the above text. Alternatively, the client may obtain the above text and send the above text to the server so that the server determines the generalization processing result corresponding to the above text.

[0103] The embodiment of the present invention can provide the following technical solution for determining the generalization processing result corresponding to the above:

[0104] Technical solution B1,

[0105] In technical solution B1, the determining of the generalization processing result corresponding to the above text may specifically include: determining the generalization processing result corresponding to the above text according to the mapping relationship between words and word categories.

[0106] Technical Solution B2,

[0107] In technical solution B2, determining the generalization processing result corresponding to the above text may specifically include: identifying at least one entity word in the above text; and replacing the at least one entity word in the above text with a corresponding entity category word.

[0108] Optionally, the entity category may include at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothing, food, medicines, vehicles, furniture, musical instruments, electrical appliances, and natural phenomena.

[0109] It should be noted that the above may include: one entity word; or, the above may include: multiple entity words. In this case, generalization processing may be performed on the multiple entity words respectively.

[0110] For example, the above text includes: entity word 3 and entity word 4, then the corresponding generalization processing methods may include: generalization processing only for entity word 3; generalization processing only for entity word 4; or generalization processing for entity word 3 and entity word 4 at the same time; therefore, the embodiment of the present invention can obtain multiple generalization processing results for one above text.

[0111] Therefore, the embodiment of the present invention may perform generalization processing on a single entity word in the above text, or may perform generalization processing on multiple entity words in the above text, thereby obtaining multiple generalization processing results.

[0112] In an application example of the present invention, the above text “Africans come to Beijing to escape the summer heat” includes: entity words “Africans” and “Beijing”, etc. Optionally, “Africans” can be generalized to “foreigners”, and the entity word “Beijing” can be generalized to “city”, etc.

[0113] In an optional embodiment of the present invention, the above-mentioned replacement of at least one entity word in the above text with a corresponding entity category word may specifically include: determining a target entity word that matches the location environment characteristics from the above text, and replacing the target entity word in the above text with a corresponding entity category word.

[0114] For example, the above text “Africans come to Beijing to escape the summer heat” includes the entity words “Africans” and “Beijing”. Assuming the location environment feature is “China”, the entity word “Beijing” matches the location environment feature, but the entity word “Africans” does not match the location environment feature. Therefore, generalization processing can be performed only on the entity word “Beijing”.

[0115] In step 302, you can follow Figure 2 In the illustrated method embodiment, at least one of the at least two elements mentioned above is generalized.

[0116] In step 302, a search may be performed in the multivariate relational data according to the generalization processing result to obtain an element matching the generalization processing result, and further obtain the first association candidate corresponding to the above text.

[0117] Specifically, the generalization processing result can be matched with any element in the multivariate relational data, for example, the generalization processing result can be matched with the first element or the second element. If the generalization processing result matches the first element, the corresponding second element can be used as the first association candidate. Alternatively, if the generalization processing result matches the second element, the corresponding first element can be used as the first association candidate.

[0118] In step 303, the client may present the first association candidate to the user, or the server may output the first association candidate to the client.

[0119] In summary, the data processing method of the embodiment of the present invention determines the first association candidate corresponding to the above text based on the generalization processing result corresponding to the above text and the multi-relation data; since the generalization processing result corresponding to the above text is obtained after generalization processing of the above text, it can include higher-level concepts; and the first element or the second element in the multi-relation data has also been generalized, so it can include higher-level concepts; therefore, the embodiment of the present invention can improve the matching rate and hit rate between the generalization processing result and the multi-relation data, and thus can improve the hit rate of the first association candidate.

[0120] Method Example 3

[0121] Reference Figure 4 , shows a flow chart of the steps of a data processing method embodiment 3 of the present invention, which may specifically include the following steps:

[0122] Step 401, determine the generalization processing result corresponding to the above text;

[0123] Step 402: determining a first association candidate corresponding to the above context according to the generalization processing result and multivariate relationship data; wherein the multivariate relationship data may include: a relationship between at least two elements, at least one of the at least two elements being generalized;

[0124] Step 403: output the first association candidate;

[0125] Relative to Figure 3 In the embodiment shown, the method of this embodiment may further include:

[0126] Step 404: Determine a second association candidate corresponding to the above context according to the context and the relationship between the third element and the fourth element; neither the third element nor the fourth element has been generalized.

[0127] The embodiment of the present invention can use the relationship between the third element and the fourth element that have not been generalized to determine the second association candidate corresponding to the above text. Specifically, the above text can be matched with the third element or the fourth element. If the generalization processing result matches the third element, the corresponding fourth element can be used as the first association candidate. Alternatively, if the generalization processing result matches the fourth element, the corresponding third element can be used as the first association candidate.

[0128] The embodiment of the present invention does not limit the execution order of step 401 and step 404 , and the execution order of the two can be: first-after-last order, last-after-last order, or parallel order.

[0129] In practical applications, if the first association candidate and the second association candidate are obtained at the same time, the first association candidate and the second association candidate can be displayed at the same time, or one of the first association candidate and the second association candidate can be displayed, for example, only the second association candidate can be displayed.

[0130] Method Example 4

[0131] Reference Figure 5 , shows a flow chart of the steps of a fourth embodiment of a data processing method of the present invention, which may specifically include the following steps:

[0132] Step 501: The client sends the above text and the generalized processing result corresponding to the above text to the server;

[0133] Step 502: The server searches for the relationship between the third element and the fourth element according to the above text. If the search is successful, step 503 is executed. Otherwise, if the search fails, step 504 is executed.

[0134] Step 503: The server outputs the second association candidate corresponding to the above text to the client;

[0135] The second association candidate may be obtained according to the relationship between the third element and the fourth element.

[0136] Step 504: The server determines a first association candidate corresponding to the above context according to the generalization processing result and the relationship between at least two elements;

[0137] Step 505: The server outputs the first association candidate corresponding to the above text to the client.

[0138] In one embodiment, the client generalizes the above text according to the semantic dictionary, and sends the user's above text and the generalization processing result to the cloud; if the above text and the relationship between the third element and the fourth element match, the corresponding second association candidate is directly given; otherwise, the generalization processing result and the relationship between at least two elements are used to obtain the first association candidate, and it is returned to the client.

[0139] It should be noted that, for the method embodiments, for the sake of simplicity of description, they are all described as a series of motion combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the described sequence of actions, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the motions involved are not necessarily required by the embodiments of the present invention.

[0140] Device Embodiment

[0141] Reference Figure 6 , shows a structural block diagram of a data processing device embodiment of the present invention, which may specifically include:

[0142] A generalization processing result determination module 601 is used to determine the generalization processing result corresponding to the above text;

[0143] A first association candidate determination module 602 is configured to determine the first association candidate corresponding to the above text according to the generalization processing result and multi-relation data; wherein the multi-relation data includes: a relationship between at least two elements, at least one of which is generalized; and

[0144] The first associative candidate output module 603 is used to output the first associative candidate.

[0145] Optionally, the generalization processing result determination module 601 may include:

[0146] The first determination module is used to determine the generalization processing result corresponding to the above text according to the mapping relationship between words and word categories.

[0147] Optionally, the generalization processing result determination module 601 may include:

[0148] A recognition module, used to recognize at least one entity word in the above text;

[0149] The second determination module is used to replace at least one entity word in the above text with a corresponding entity category word.

[0150] Optionally, the entity category may include at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothing, food, medicines, vehicles, furniture, musical instruments, electrical appliances, and natural phenomena.

[0151] Optionally, the device may further include:

[0152] A generalization processing module, used for generalizing the left element in the multivariate relational data to obtain the first element;

[0153] The relationship determination module is used to obtain the relationship between the first element and the second element according to the first element and the right element in the multi-element relationship data.

[0154] Optionally, the device may further include:

[0155] The second association candidate determination module is used to determine the second association candidate corresponding to the above context according to the above context and the relationship between the third element and the fourth element; the third element and the fourth element are not generalized.

[0156] Optionally, the element may include at least one of: words, phrases, short sentences, letters, numbers and symbols.

[0157] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0158] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0159] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0160] An embodiment of the present invention provides a device for data processing, including a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: determining a generalization processing result corresponding to the above text; determining a first association candidate corresponding to the above text based on the generalization processing result and multivariate relationship data; wherein the multivariate relationship data includes: a relationship between at least two elements, at least one of the at least two elements being generalized; and outputting the first association candidate.

[0161] Figure 78 is a block diagram of a data processing apparatus 800 according to an exemplary embodiment. For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0162] Reference Figure 7 , the device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0163] The processing component 802 generally controls the overall operation of the device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0164] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0165] The power supply component 806 provides power to the various components of the device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 800.

[0166] The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0167] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the device 800 is in an operating mode, such as a call mode, a recording mode, and a voice input mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0168] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0169] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800, and the sensor assembly 814 can also detect the position change of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration / deceleration of the device 800, and the temperature change of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0170] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID, Radio Frequency Identification) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0171] In an exemplary embodiment, the apparatus 800 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 method.

[0172] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0173] Figure 8 1 is a schematic diagram of the structure of the server in some embodiments of the present invention. The server 1900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 can be short-term storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server. Furthermore, the central processing unit 1922 can be configured to communicate with the storage medium 1930 and execute a series of instruction operations in the storage medium 1930 on the server 1900.

[0174] The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1958, one or more keyboards 1956, and / or, one or more operating systems 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0175] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to perform Figure 2 or Figure 3 The data processing method shown.

[0176] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by the processor of a device (server or terminal), the device is able to execute a data processing method, the method comprising: determining a generalization processing result corresponding to the above; determining a first association candidate corresponding to the above based on the generalization processing result and multivariate relationship data; wherein the multivariate relationship data comprises: a relationship between at least two elements, at least one of the at least two elements being generalized; and outputting the first association candidate.

[0177] The embodiment of the present invention discloses A1, a data processing method, the method comprising:

[0178] Determine the generalization processing result corresponding to the above text;

[0179] Determining the first association candidate corresponding to the above context according to the generalization processing result and multi-relation data; wherein the multi-relation data includes: a relationship between at least two elements, at least one of the at least two elements being generalized;

[0180] The first association candidate is output.

[0181] A2. According to the method described in A1, determining the generalization processing result corresponding to the above text includes:

[0182] According to the mapping relationship between words and word categories, the corresponding generalization processing result of the above text is determined.

[0183] A3. According to the method described in A1, determining the generalization processing result corresponding to the above text includes:

[0184] Identify at least one entity word in the above context;

[0185] At least one entity word in the above text is replaced with a corresponding entity category word.

[0186] A4. According to the method described in A3, the entity category includes at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothing, food, medicine, transportation, furniture, musical instruments, electrical appliances, and natural phenomena.

[0187] A5. The method according to A1, further comprising:

[0188] Generalize the left element in the multivariate relational data to obtain the first element;

[0189] The relationship between the first element and the second element is obtained according to the first element and the right element in the multi-element relationship data.

[0190] A6. The method according to A1, further comprising:

[0191] According to the above context and the relationship between the third element and the fourth element, a second association candidate corresponding to the above context is determined; the third element and the fourth element are not generalized.

[0192] A7. According to any of the methods described in A1 to A6, the elements include at least one of words, phrases, short sentences, letters, numbers and symbols.

[0193] The embodiment of the present invention discloses B8, a data processing device, including:

[0194] A generalization processing result determination module, used to determine the generalization processing result corresponding to the above text;

[0195] A first association candidate determination module is configured to determine a first association candidate corresponding to the above text according to the generalization processing result and multivariate relationship data; wherein the multivariate relationship data includes: a relationship between at least two elements, at least one of the at least two elements being generalized; and

[0196] The first association candidate output module is used to output the first association candidate.

[0197] B9. According to the device described in B8, the generalization processing result determination module includes:

[0198] The first determination module is used to determine the generalization processing result corresponding to the above text according to the mapping relationship between words and word categories.

[0199] B10. According to the device described in B8, the generalization processing result determination module includes:

[0200] A recognition module, used to recognize at least one entity word in the above text;

[0201] The second determination module is used to replace at least one entity word in the above text with a corresponding entity category word.

[0202] B11. According to the device described in B10, the entity category includes at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothes, food, medicine, transportation, furniture, musical instruments, electrical appliances, and natural phenomena.

[0203] B12. The device according to B8, further comprising:

[0204] A generalization processing module, used for generalizing the left element in the multivariate relational data to obtain the first element;

[0205] The relationship determination module is used to obtain the relationship between the first element and the second element according to the first element and the right element in the multi-element relationship data.

[0206] B13. The device according to B8, further comprising:

[0207] The second association candidate determination module is used to determine the second association candidate corresponding to the above context according to the above context and the relationship between the third element and the fourth element; the third element and the fourth element are not generalized.

[0208] B14. According to any one of the devices described in B8 to B13, the elements include at least one of words, phrases, short sentences, letters, numbers and symbols.

[0209] The embodiment of the present invention discloses C15, a device for data processing, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations:

[0210] Determine the generalization processing result corresponding to the above text;

[0211] Determining the first association candidate corresponding to the above context according to the generalization processing result and multi-relation data; wherein the multi-relation data includes: a relationship between at least two elements, at least one of the at least two elements being generalized;

[0212] The first association candidate is output.

[0213] C16. According to the apparatus described in C15, the determining of the generalization processing result corresponding to the above text includes:

[0214] According to the mapping relationship between words and word categories, the corresponding generalization processing result of the above text is determined.

[0215] C17. According to the apparatus described in C15, the determining of the generalization processing result corresponding to the above text includes:

[0216] Identify at least one entity word in the above context;

[0217] At least one entity word in the above text is replaced with a corresponding entity category word.

[0218] C18. According to the device described in C17, the entity category includes at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothes, food, medicine, transportation, furniture, musical instruments, electrical appliances, and natural phenomena.

[0219] C19. The device according to C15, wherein the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0220] Generalize the left element in the multivariate relational data to obtain the first element;

[0221] The relationship between the first element and the second element is obtained according to the first element and the right element in the multi-element relationship data.

[0222] C20. The device according to C15, wherein the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0223] According to the above context and the relationship between the third element and the fourth element, a second association candidate corresponding to the above context is determined; the third element and the fourth element are not generalized.

[0224] C21. According to any one of the devices described in C15 to C20, the elements include at least one of words, phrases, short sentences, letters, numbers and symbols.

[0225] The embodiment of the present invention discloses D22, a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes the device to execute the data processing method as described in one or more of A1 to A7.

[0226] Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0227] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0228] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0229] The data processing method, the data processing device and the device for data processing provided by the present invention are introduced in detail above. The principle and implementation mode of the present invention are explained by using specific examples in this article. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and the scope of application. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A data processing method, It is characterized in that The method comprises: Identify a target entity word in the above text that matches the location environment feature corresponding to the above text; According to the mapping relationship between words and word categories, the target entity words in the above text are replaced with corresponding entity category words to obtain the corresponding generalization processing result in the above text; Searching in the multivariate relational data according to the generalization processing result to determine an element matching the generalization processing result; Determine the first association candidate corresponding to the above context according to the element in the multivariate relationship data that matches the generalization processing result; wherein the multivariate relationship data includes: a relationship between at least two elements, at least one of the at least two elements is generalized, and the multivariate relationship data is used to represent the probability of the at least two elements appearing successively; wherein, when the multivariate relationship data contains a first element and a second element, if the generalization processing result matches the first element in the multivariate relationship data, then the second element in the multivariate relationship data is determined as the first association candidate corresponding to the above context, or, if the generalization processing result matches the second element in the multivariate relationship data, then the first element in the multivariate relationship data is determined as the first association candidate corresponding to the above context; The first association candidate is output.

2. The method according to claim 1, It is characterized in that The entity category includes at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothing, food, medicines, vehicles, furniture, musical instruments, electrical appliances, and natural phenomena.

3. The method according to claim 1, It is characterized in that The method further comprises: Generalize the left element in the multivariate relational data to obtain the first element; The relationship between the first element and the second element is obtained according to the first element and the right element in the multi-element relationship data.

4. The method according to claim 1, It is characterized in that The method further comprises: According to the above context and the relationship between the third element and the fourth element, a second association candidate corresponding to the above context is determined; the third element and the fourth element are not generalized.

5. The method according to any one of claims 1 to 4, It is characterized in that The elements include at least one of words, phrases, short sentences, letters, numbers and symbols.

6. A data processing device, It is characterized in that include: A recognition module, used to recognize a target entity word in the above text that matches the location environment feature corresponding to the above text; A first determination module is used to replace the target entity word in the above text with a corresponding entity category word according to a mapping relationship between words and word categories, so as to obtain a generalization processing result corresponding to the above text; A first association candidate determination module, used to search in the multivariate relational data according to the generalization processing result, and determine an element matching the generalization processing result; Determining the first association candidate corresponding to the above context according to the element in the multivariate relationship data that matches the generalization processing result; wherein the multivariate relationship data includes: a relationship between at least two elements, at least one of the at least two elements is generalized, and the multivariate relationship data is used to represent the probability of the at least two elements appearing successively; wherein, when the multivariate relationship data contains a first element and a second element, if the generalization processing result matches the first element in the multivariate relationship data, the second element in the multivariate relationship data is determined as the first association candidate corresponding to the above context, or, if the generalization processing result matches the second element in the multivariate relationship data, the first element in the multivariate relationship data is determined as the first association candidate corresponding to the above context; and The first association candidate output module is used to output the first association candidate.

7. The device according to claim 6, It is characterized in that The entity category includes at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothing, food, medicines, vehicles, furniture, musical instruments, electrical appliances, and natural phenomena.

8. The device according to claim 6, It is characterized in that The device also includes: A generalization processing module, used for generalizing the left element in the multivariate relational data to obtain the first element; The relationship determination module is used to obtain the relationship between the first element and the second element according to the first element and the right element in the multi-element relationship data.

9. The device according to claim 6, It is characterized in that The device also includes: The second association candidate determination module is used to determine the second association candidate corresponding to the above context according to the above context and the relationship between the third element and the fourth element; the third element and the fourth element are not generalized.

10. The device according to any one of claims 6 to 9, It is characterized in that The elements include at least one of words, phrases, short sentences, letters, numbers and symbols.

11. A device for data processing, It is characterized in that The invention comprises a memory and one or more programs, wherein the one or more programs are stored in the memory, and when the programs are executed by one or more processors, the steps of the method described in any one of claims 1 to 5 are implemented.

12. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, cause an apparatus to perform a data processing method as claimed in one or more of claims 1 to 5.

Citation Information

Patent Citations

  • Method and system for automatically generating semantic template of problem

    CN101369265A

  • An associating method and device for candidate words of an input method

    CN109002184A

  • A data processing method and device

    CN109739968A

  • Searching method, terminal and medium

    CN109992689A

  • Word prediction for numbers and symbols

    US9298276B1