Method and apparatus for processing personalized word library

Abstract

An embodiment of the present invention provides a method for processing a personalized vocabulary, a device, and a device for processing a personalized vocabulary. The method specifically includes: determining user status information; the user status information includes: matching information between the user's input content and feature entries, and / or updated information on the geographical location where the user is located; if the user status information meets a preset condition, the first personalized vocabulary corresponding to the user status information is provided to the user. The embodiment of the present invention can reduce the operation cost of the user's word-by-word selection and screen input, thereby improving the input efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of input, and particularly to a method and apparatus for processing a personalized word library. Background Art

[0002] Currently, for devices involving interaction, users usually need to interact and identify their operation intentions with the devices through an input method system. For example, a user can input an input string, and then the input method program converts the input string into candidates in a corresponding language according to its preset mapping rules and displays them, and then screens the candidates selected by the user.

[0003] Currently, the input method program can parse the input string input by the user. For example, if the input string input by the user is a pinyin string, the corresponding entry can be obtained by querying the mapping relationship between the pinyin string and the entry stored in the word library, and then the queried entry is displayed to the user as a candidate.

[0004] The inventor found during the implementation of the embodiments of the present invention that if there is no entry corresponding to the pinyin string input by the user in the word library, it is usually necessary to select and screen the single characters included in the target entry one by one to complete the input of the target entry; this not only makes the input process cumbersome, but also affects the input efficiency. For example, if a user wants to input the target entry "liduanji" through the pinyin string "liduanji", but there is no "liduanji" in the word library, so the user needs to select and screen the single characters "li", "duan", and "ji" one by one. The selection and screening of single characters require a lot of operation costs, resulting in low input efficiency. Summary of the Invention

[0005] Embodiments of the present invention provide a method and apparatus for processing a personalized word library and an apparatus for input, which can reduce the operation cost of the user selecting and screening characters one by one, and thus improve the input efficiency.

[0006] To solve the above problems, embodiments of the present invention disclose a method for processing a personalized word library, including:

[0007] Determine user status information; the user status information includes: matching information between the user's input content and feature entries, and / or updated information on the geographical location where the user is located;

[0008] If the user status information meets a preset condition, provide the user with a first personalized word library corresponding to the user status information.

[0009] On the other hand, embodiments of the present invention disclose a device for processing a personalized word library, including:

[0010] A user status information determination module for determining user status information; the user status information includes: matching information between the user's input content and feature entries, and / or updated information on the geographical location where the user is located; and

[0011] A first providing module for providing the user with a first personalized lexicon corresponding to the user status information if the user status information meets a preset condition.

[0012] In another aspect, an embodiment of the present invention discloses a device for processing a personalized lexicon, 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. The one or more programs include instructions for performing the following operations:

[0013] Determine user status information; the user status information includes: matching information between the user's input content and feature entries, and / or updated information on the geographical location where the user is located;

[0014] If the user status information meets a preset condition, provide the user with a first personalized lexicon corresponding to the user status information.

[0015] In yet another aspect, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon that, when executed by one or more processors, cause the device to perform the method for processing a personalized lexicon as described in one or more of the foregoing.

[0016] The embodiments of the present invention include the following advantages:

[0017] In the case where the user status information meets a preset condition, the embodiment of the present invention provides the user with a first personalized lexicon corresponding to the user status information. Since the user status information can be real-time information during the user's use of the device, the first personalized lexicon can meet the real-time personalized needs corresponding to the user status information. Using the first personalized lexicon in the user's input process can, based on the characteristic that the first personalized lexicon conforms to the real-time personalized needs, increase the hit probability of the target entry that the user wants to input for the first personalized lexicon. Therefore, the operation cost of the user's word-by-word selection and screen input can be reduced, and thus the input efficiency can be improved.

[0018] In the case where the user status information includes the matching information between the user's input content and feature entries, the embodiment of the present invention can provide a first personalized lexicon corresponding to the user's real-time personalized needs based on the input content that matches the feature entries.

[0019] In the case where the user status information includes the updated information of the geographical location where the user is located, the real-time personalized needs of the user can be related to the updated geographical location. Therefore, the embodiments of the present invention can provide a first personalized thesaurus corresponding to the updated geographical location to help the user improve the input efficiency of the entries corresponding to the updated geographical location. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the description of the embodiments of the present invention. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 is a schematic diagram of the application environment of a method for processing a personalized thesaurus according to an embodiment of the present invention;

[0022] Figure 2 is a flowchart of the steps of Embodiment 1 of a method for processing a personalized thesaurus according to the present invention;

[0023] Figure 3 is a flowchart of the steps of Embodiment 2 of a method for processing a personalized thesaurus according to the present invention;

[0024] Figure 4 is a flowchart of the steps of Embodiment 3 of a method for processing a personalized thesaurus according to the present invention;

[0025] Figure 5 is a flowchart of the steps of Embodiment 4 of a method for processing a personalized thesaurus according to the present invention;

[0026] Figure 6 is a flowchart of the steps of Embodiment 5 of a method for processing a personalized thesaurus according to the present invention;

[0027] Figure 7 is a block diagram of the structure of an embodiment of a device for processing a personalized thesaurus according to the present invention;

[0028] Figure 8 is a block diagram of a device 800 for processing a personalized thesaurus according to the present invention; and

[0029] Figure 9 is a schematic diagram of the structure of a server in some embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0031] In view of the technical problem of low input efficiency in the traditional technology, the embodiments of the present invention provide a processing solution for a personalized word library, which can determine user status information; the above user status information specifically includes: the matching information between the user's input content and the feature entries, and / or, the updated information of the geographical location where the user is located; if the above user status information meets the preset conditions, the first personalized word library corresponding to the above user status information is provided to the user.

[0032] In the case where the user status information in the embodiments of the present invention meets the preset conditions, the first personalized word library corresponding to the user status information is provided to the user. Since the user status information can be real-time information during the user's use of the device, the first personalized word library can meet the real-time personalized needs corresponding to the user status information. Using the first personalized word library in the user's input process, based on the characteristic that the first personalized word library conforms to the real-time personalized needs, the hit probability of the target entry that the user wants to input for the first personalized word library can be increased. Therefore, the operation cost of the user's word-by-word selection and posting can be reduced, and the input efficiency can be improved.

[0033] In the case where the user status information includes the matching information between the user's input content and the feature entries, the embodiments of the present invention can provide the first personalized word library corresponding to the user's real-time personalized needs according to the input content that matches the feature entries.

[0034] For example, if the real-time personalized needs are related to topic A, then in the case where the user inputs input content related to topic A, the first personalized word library provided by the embodiments of the present invention may include: a set of entries related to topic A, to help the user improve the input efficiency of entries related to topic A. The topic can represent the title of a conversation or the theme being discussed. For example, topic A can be related to film and television dramas, games, learning to drive, decoration, etc. It can be understood that the embodiments of the present invention do not limit the specific topic.

[0035] When the user status information includes the updated information of the geographical location where the user is located, the real-time personalized needs of the user can be related to the updated geographical location. Therefore, the embodiments of the present invention can provide a first personalized thesaurus corresponding to the updated geographical location. For example, when user B is traveling in city X, a first personalized thesaurus corresponding to city X is provided to user B. The first personalized thesaurus corresponding to city X may include: POI entries corresponding to POIs (points of information), such as scenic spots, hotels, restaurants, etc. in city X, to help the user improve the input efficiency of POI entries.

[0036] The method for processing the personalized thesaurus provided by the embodiments of the present invention can be applied to Figure 1 the application environment shown in Figure 1 As shown, the client 100 and the server 200 are located in a wired or wireless network. Through the wired or wireless network, the client 100 and the server 200 perform data interaction.

[0037] Optionally, the client 100 can run on a terminal. The above terminal specifically includes but is not limited to: smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, in-vehicle computers, desktop computers, set-top boxes, smart televisions, wearable devices, and so on. The client 100 can correspond to a website or an APP (application).

[0038] The server in the embodiments of the present invention can be a cloud server (cloud). The cloud is a simple, efficient, secure, and reliable computing service with elastic scalability of processing power. The resource information of the cloud is dynamic, enabling its processing power to be elastically scalable.

[0039] The embodiments of the present invention can be applied to input method programs for various input methods such as keyboard symbols, handwriting, and voice. That is, the user can input text through an encoded string, and the input string can refer to the encoded string input by the user. In the field of input methods, for input method programs for languages such as Chinese, Japanese, Korean, or other languages, the input string input by the user is usually 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 may include but is not limited to full pinyin, simple pinyin, strokes, Wubi, etc. The embodiments of the present invention do not limit the specific input method program corresponding to a certain language.

[0040] Taking Chinese input as an example, the types of encoded strings can include: pinyin strings, glyph strings (such as Wubi strings, etc.). Taking English input as an example, the types of encoded strings can include: alphabetic strings, etc.

[0041] In practical applications, for the input method of keyboard symbols, the user can input the above input strings through a physical keyboard or a virtual keyboard, etc. For example, for a terminal with a touch screen, it can set a virtual keyboard 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 can include: a 9-key keyboard and a 26-key keyboard, etc. And it can be understood that in addition to setting virtual keys corresponding to letters in the above input interface, symbol keys, number keys, function keys such as Chinese-English switching keys, or toolbar keys can also be set. It can be understood that the specific keys included in the input interface in the embodiments of the present invention are not limited.

[0042] According to some embodiments, the above input string can include but is not limited to: a combination of one or more key symbols input by the user through a key. The key symbol can specifically include: pinyin, strokes, kana, etc.

[0043] In the embodiments of the present invention, candidates can be used to represent one or more characters provided by the input method program to be selected by the user. The candidates can correspond to the context, or the candidates can correspond to the input string, or the candidates can correspond to the input string and the context. The candidates can be characters in languages such as Chinese characters, English characters, Japanese characters, etc., and the candidates can also be symbol combinations in the form of kaomoji, pictures, etc. Among them, the kaomoji includes but is not limited to pictures composed of lines, symbols, and characters. For example, examples of the kaomoji can include: ":P", ": - o", ": - )", etc.

[0044] In the embodiments of the present invention, based on the input string, a search can be performed in the thesaurus to obtain the candidates corresponding to the input string. The above thesaurus can be a traditional thesaurus, and the above traditional thesaurus specifically includes: a system thesaurus, a user thesaurus, a cell thesaurus, a cloud thesaurus, etc. The embodiments of the present invention add a first personalized thesaurus on the basis of the traditional thesaurus to meet the real-time personalized needs of users.

[0045] Method Embodiment 1

[0046] Referring to Figure 2 , a flowchart of the steps of Method Embodiment 1 for processing a personalized thesaurus of the present invention is shown, which can specifically include the following steps:

[0047] Step 201, determine the user status information; the user status information specifically includes: the matching information between the user's input content and the feature entries, and / or the updated information of the geographical location where the user is located;

[0048] Step 202, if the above user status information meets the preset conditions, provide the user with the first personalized thesaurus corresponding to the above user status information.

[0049] Figure 2 The method embodiments shown can be executed by the client and / or the server. It can be understood that the embodiments of the present invention do not limit the specific execution entity of the method embodiments.

[0050] In step 201, the input content of the user can be received, and the input content is matched with the feature entries to obtain the matching information between the two. The matching information can include: matching or not matching.

[0051] In the embodiments of the present invention, the feature words can represent words with exclusive characteristics, which can meet certain personalized needs of users. The above feature entries specifically include at least one of domain entries, self-created entries, and cloud entries.

[0052] Among them, the domain can refer to a certain professional scope, and all matters involved in this scope can be cited. Domain vocabulary can refer to the vocabulary within the domain scope, and domain vocabulary can correspond to domain keywords.

[0053] The embodiments of the present invention can determine the domain vocabulary by the following determination methods.

[0054] Determination method 1, determine the domain vocabulary of the personal characteristic category, and the personal characteristic category can correspond to domain keywords.

[0055] The domain vocabulary of the personal characteristic category specifically includes: professional attribute categories (doctor, courier...); long-term interest categories (anime second dimension, military...), etc.

[0056] Determination method 2, determine the domain vocabulary of the topic category, and the topic category can correspond to domain keywords.

[0057] The domain vocabulary of the topic category specifically includes: temporary topics (raising fish, a certain TV drama...); phased topics (such as buying insurance, buying a house, learning to drive, decorating...), etc.

[0058] Determination method 3, grab cell entries from the cell thesaurus of the website, and after screening the grabbed cell entries, mark the corresponding domain keywords.

[0059] Determination method 4, cluster the high-frequency entries input by the user, use the corresponding category keywords as domain keywords, and use the high-frequency entries under the category as domain entries.

[0060] It can be understood that Determination Method 1 to Determination Method 4 are only examples of the determination methods for domain vocabulary. The embodiments of the present invention do not limit the specific determination methods for domain vocabulary. Those skilled in the art can also adopt other determination methods according to actual application requirements. For example, entity words can be collected and used as domain vocabulary.

[0061] In the embodiments of the present invention, an entity is a specific thing or concept. Entities are generally classified, such as entity types of people, movies, animals, history, etc. The same entity can correspond to multiple entity instances. An entity instance can be a descriptive page (content) of an entity in a network (or other media). For example, the page of an encyclopedia contains entity instances corresponding to the entity.

[0062] Optionally, an entity may include: named entity, which can refer to a person's name, an organization's name, a place name, and all other entities identified by a name. More extensive named entities can also include: book titles, song titles, movie and TV drama names, product names, brand names, numbers, dates, currencies, addresses, etc.

[0063] Optionally, the entity category may include at least one of the following categories: people, places, fruits, vegetables, animals, plants, buildings, clothing, food, drugs, transportation means, furniture, musical instruments, electrical appliances, and natural phenomena. The entity category can be used as a domain keyword.

[0064] The self-created entry can be an entry created by the user to supplement the deficiencies of the traditional thesaurus. In practical applications, a self-created entry interface can be provided to receive the mapping relationship between the input string set by the user and the self-created entry.

[0065] The cloud entry can be an entry provided by the cloud based on the cloud input method and can be used as a supplement to the entries in the traditional thesaurus. The cloud input method is an input method relying on cloud computing technology. With the powerful storage and computing capabilities of the server cluster, it has advantages that traditional input methods cannot match: a larger and newer thesaurus, a more advanced language model, and these advantages have significantly improved the input accuracy. In practical applications, a cloud request can be sent to the cloud. The cloud request can include an input string, and the cloud entry returned by the cloud can be received.

[0066] In the embodiments of the present invention, the geographical location is generally used to describe the temporal and spatial relationships of geographical things. According to different needs of users, different methods can be used to qualitatively and quantitatively locate geographical things, so as to grasp the spatio-temporal attributes and related characteristics of geographical things.

[0067] Optionally, the types of the above-mentioned geographical locations specifically include at least one of the following types: administrative regions, communities, streets, and buildings. It can be understood that the embodiments of the present invention do not limit the specific types of geographical locations.

[0068] An administrative region is a regional division implemented by a country for hierarchical management. For example, a country is divided into provinces, autonomous regions, and municipalities directly under the Central Government; provinces and autonomous regions are divided into cities, counties, autonomous prefectures, and autonomous counties; counties and autonomous counties are divided into townships, towns, and ethnic townships, etc.

[0069] An embodiment of the present invention can store the feature entry set locally and match the input content with the feature entry set to obtain corresponding matching information. However, the feature entry set usually occupies a certain amount of storage space.

[0070] In another embodiment of the present invention, the above method may further include: adding a feature entry mark to the local entries in the local thesaurus; if the local entries hit by the user's input content carry a feature entry mark, then the input content matches the feature entry.

[0071] The embodiments of the present invention add a feature entry mark to the local entries in the local thesaurus that match the feature entry, and determine whether the input content matches the feature entry according to whether the local entries hit by the input content carry a feature entry mark. The embodiments of the present invention can save the storage space occupied by the feature entry set.

[0072] The embodiments of the present invention can determine the geographical location where the user is located according to the geographical location corresponding to the terminal, and detect whether the geographical location where the user is located is updated.

[0073] In an alternative embodiment of the present invention, the geographical location may be longitude and latitude information. The longitude and latitude information can be determined according to a first period, and the first period can be 1 hour, etc. Moreover, the distance between two adjacent longitude and latitude information can be judged. If the distance is greater than a distance threshold (such as 100 kilometers), it can be judged whether there is an update of the city. For example, an update detection request can be sent to the server. If the server returns an update flag, it is considered that a city update has occurred. If the server returns a non-update flag, it is considered that no city update has occurred.

[0074] In step 202, the preset condition can be used as a condition for providing the first personalized thesaurus.

[0075] Those skilled in the art can determine the above-mentioned preset conditions according to actual application requirements. For example, the above-mentioned preset conditions specifically include:

[0076] The first preset condition: the number of input contents matching the feature entry exceeds a threshold; and / or

[0077] Second preset condition: The geographical location where the user is located is updated.

[0078] The first preset condition may be that the number of matches between the input content and the feature entries exceeds a threshold. In this case, it indicates that the user has real-time personalized needs corresponding to the feature entries, so the first personalized thesaurus can be provided to the user. Those skilled in the art can determine the threshold according to actual application requirements. For example, the threshold can be a natural number greater than 0, and the threshold can be 2, etc.

[0079] The second preset condition may be that the geographical location where the user is located is updated, that is, the user has reached a new geographical location. In this case, it indicates that the user has real-time personalized needs corresponding to the updated geographical location, so the first personalized thesaurus can be provided to the user.

[0080] In an embodiment of the present invention, optionally, the above first personalized thesaurus specifically includes at least one of the following entries:

[0081] Personalized entry 1, domain entries in the first target domain where the domain keyword matches the input content;

[0082] Personalized entry 2, related entries that have a vector matching relationship with the input content;

[0083] Personalized entry 3, entries corresponding to the updated geographical location;

[0084] Personalized entry 4, entries that match the input content and its context.

[0085] For personalized entry 1, in an embodiment of the present invention, the input content can be matched with the domain keyword. For example, the input content of user A includes: "bug net", "monkey", "Tarantula Island", etc. The above input content matches the domain keyword "Animal Crossing", so the domain entries in the game domain corresponding to the domain keyword "Animal Crossing" can be recommended to user A as personalized entries. The domain entries in the game domain corresponding to the domain keyword "Animal Crossing" specifically include: "Nook Stop", "Fudon", "Ryuya", etc.

[0086] For personalized entry 2, in an embodiment of the present invention, the input content can be converted into a first word vector, and according to the vector matching relationship, a second word vector that matches the first word vector can be obtained, and the entry corresponding to the second word vector is used as personalized entry 2.

[0087] Word vector technology can convert words into dense vectors. And for words with similar semantics and / or contexts, their corresponding word vectors are also similar. The dense-dimensional word vectors can contain more information, and a single dimension of the word vector can have a specific meaning.

[0088] For example, the number of dimensions of the word vectors can include: 128 or 256 or 512 or 1024, etc. The word vectors after training can represent the matching relationships between words. For example, the distance between "banana" and "apple" is closer than the distance between "banana" and "eggplant". Therefore, the matching degree between "banana" and "apple" is greater than the matching degree between "banana" and "eggplant".

[0089] Multiple word vectors can be fused into a new word vector. For example, word vector "woman" + word vector "beautiful" = word vector "goddess". Subtracting one word vector from another word vector can obtain a new vector. For example, word vector "king" - word vector "man" + word vector "woman" = word vector "queen", etc.

[0090] For the personalized entry 3, POI entries corresponding to scenic spots, hotels, restaurants, etc. corresponding to the updated geographical location can be provided to help improve the input efficiency of the user for the POI entries.

[0091] For the personalized entry 4, the context of the input content can be used in the determination process of the personalized entry, which can improve the accuracy in the corresponding field of the personalized entry.

[0092] For example, the input content includes "monkey", and this input content corresponds to fields such as "animal" and "Animal Crossing". Embodiments of the present invention can combine the context of this input content, such as "the reactions of hitting different small animals with a bug net" and "the monkey leaving angrily after being ignored", etc., to determine that this input content corresponds to the field of "Animal Crossing".

[0093] In embodiments of the present invention, the context can include: the above text, and / or, the below text. Optionally, the above text is usually the part before the input content, and the below text is usually the part after the input content.

[0094] In an alternative embodiment of the present invention, providing the first personalized thesaurus corresponding to the user status information to the user specifically includes: if a preset condition is met, sending a request to the server; the request may include: the above user status information; receiving the first personalized thesaurus returned by the server according to the request.

[0095] Optionally, the above request may further include: the context of the input content. The context may include: a preset number of words before and after the input content, and the preset number may be 5 to 10. It can be understood that embodiments of the present invention do not limit the specific preset number.

[0096] The server can use a recommendation method to determine the first personalized lexicon corresponding to the user status information. For example, the recommendation method can include: matching the input content and / or context with domain keywords to obtain personalized entry 1. Another example is that the recommendation method can include: converting the input content into a first word vector, and based on the vector matching relationship, obtaining a second word vector that matches the first word vector, and using the entry corresponding to the second word vector as personalized entry 2. Still another example is that the recommendation method can include: using the POI entry corresponding to the updated geographical location as personalized entry 3. It can be understood that the embodiments of the present invention do not limit the specific recommendation method.

[0097] The embodiments of the present invention provide the user with the first personalized lexicon corresponding to the user status information, specifically including: downloading the first lexicon file corresponding to the first personalized lexicon from the server, and loading the first lexicon file locally to use the loaded first lexicon file to provide services to the user.

[0098] In the embodiments of the present invention, the first personalized lexicon may include information such as input strings, personalized entries, tags, and word frequencies. Among them, the tag can represent the corresponding recommendation method. If a personalized entry with a tag is hit, the parameters of the corresponding recommendation method can be updated according to the corresponding hit information.

[0099] During the user's input process, according to the user's input string, a search can be performed in the first personalized lexicon. If the search hits, the corresponding personalized entry can be used as a candidate. For example, user A wants to input the target entry "liduanji" through the pinyin string "liduanji", but the entry "liduanji" does not exist in the traditional lexicon. However, the first personalized lexicon provided according to user A's input content includes "liduanji". Therefore, the candidate "liduanji" can be provided based on the first personalized lexicon. Since it can save the operation costs consumed by single-character selection and input, the input efficiency can be improved.

[0100] In the embodiments of the present invention, optionally, the candidates can be sorted according to the priority of the candidate types. The candidate types can include: user lexicon type, error correction type, system lexicon type, personalized lexicon type, cloud type, word formation type, etc.

[0101] Examples of the above priorities can include: user lexicon type > error correction type > system lexicon type & personalized lexicon type > cloud type > word formation type, etc. For example, the pinyin string "liduanji" hits the first personalized lexicon, but does not hit the user lexicon and the system lexicon, and there is no corresponding error correction candidate. Therefore, the candidate corresponding to the hit personalized entry "liduanji" can be placed at the top of the candidates. It can be understood that the embodiments of the present invention do not limit the specific priorities.

[0102] In an embodiment of the present invention, optionally, the first personalized thesaurus corresponds to a first time limit value. The above method may further include: if the time corresponding to the first time limit value is reached, deleting the first personalized thesaurus. After the time limit corresponding to the first time limit value arrives, cleaning the first personalized thesaurus can release the space corresponding to the first personalized thesaurus. The initial value of the first time limit value may be a duration such as 48 hours, 72 hours, etc.

[0103] Optionally, the above method may further include: if the subsequent input content of the user hits the first personalized thesaurus, increasing the first time limit value corresponding to the first personalized thesaurus. For example, if the subsequent input content hits the first personalized thesaurus, the first time limit value corresponding to the first personalized thesaurus is restored to the initial value. Another example is that if the hit count of the first personalized thesaurus exceeds the count threshold, a preset value is added to the first time limit value, and the hit count is cleared. The preset value may be a preset ratio of the initial value, such as 1 / 3. For example, every time the hit count of the first personalized thesaurus exceeds 5 times, 24 hours is added to the first time limit value.

[0104] If the subsequent input content of the user hits the first personalized thesaurus, it indicates that the field corresponding to the first personalized thesaurus meets the real-time personalized needs of the user. In this case, increasing the first time limit value corresponding to the first personalized thesaurus can increase the service duration of the first personalized thesaurus for the user.

[0105] It should be noted that if the subsequent input content of the user does not hit the first personalized thesaurus, the user status information may be determined based on the subsequent input content to continuously provide the first personalized thesaurus.

[0106] It can be understood that on the terminal local of the embodiment of the present invention, one or more first personalized thesauruses can be provided for the user to provide corresponding personalized input services. Among them, different first personalized thesauruses can be independent of each other. For example, the deletion of one first personalized thesaurus does not affect another first personalized thesaurus. Another example is that the hit of one first personalized thesaurus does not affect another first personalized thesaurus.

[0107] In summary, for the method for processing the personalized thesaurus in the embodiment of the present invention, when the user status information meets the preset conditions, the first personalized thesaurus corresponding to the user status information is provided to the user. Since the user status information can be real-time information during the user's use of the device, the first personalized thesaurus can meet the real-time personalized needs corresponding to the user status information. Using the first personalized thesaurus in the user's input process can, based on the characteristic that the first personalized thesaurus conforms to the real-time personalized needs, improve the hit probability of the target entry that the user wants to input for the first personalized thesaurus. Therefore, the operation cost of the user's word-by-word selection and on-screen display can be reduced, and the input efficiency can be improved.

[0108] When the user status information includes the matching information between the user's input content and the feature entries, the embodiments of the present invention can provide a first personalized thesaurus corresponding to the user's real-time personalized needs according to the input content that matches the feature entries.

[0109] When the user status information includes the updated information of the geographical location where the user is located, the user's real-time personalized needs may be related to the updated geographical location. Therefore, the embodiments of the present invention can provide a first personalized thesaurus corresponding to the updated geographical location to help the user improve the input efficiency of the entries corresponding to the updated geographical location.

[0110] Method Embodiment Two

[0111] Refer to Figure 3 , which shows the flowchart of the steps of Method Embodiment Two of a method for processing a personalized thesaurus according to the present invention, and specifically may include the following steps:

[0112] Step 301, determine the user status information; the above user status information specifically includes: the matching information between the user's input content and the feature entries, and / or, the updated information of the geographical location where the user is located;

[0113] Step 302, if the above user status information meets the preset conditions, provide the user with a first personalized thesaurus corresponding to the above user status information;

[0114] Relative to Figure 2 the method shown in Method Embodiment One, the method of this embodiment may further include:

[0115] Step 303, provide the user with a second personalized thesaurus according to a preset period; the above second personalized thesaurus may be obtained from the historical input content input by the user within a preset time period, and / or, the user's common geographical location.

[0116] The embodiments of the present invention can provide the user with a second personalized thesaurus that meets their long-term personalized needs according to the historical input content input by the user within a preset time period.

[0117] The long-term personalized needs may include: professional needs, interest needs, etc. For example, if the profession of user B is "medicine", personalized entries related to medicine can be recommended to him. Another example is that if the interest characteristics of user C include "second dimension", personalized entries related to "second dimension" can be recommended to him.

[0118] The embodiments of the present invention can also recommend POI entries within the user's common geographical location to the user. The common geographical location specifically includes: home or unit, etc. The above POI entries specifically include: entries of merchants, communities, streets, etc. around the common geographical location.

[0119] In the embodiments of the present invention, the frequently used geographical locations can be determined based on the duration of maintenance of the geographical location where the user is located. It can be understood that the embodiments of the present invention do not limit the specific determination method of the frequently used geographical locations.

[0120] In practical applications, the client can regularly send historical input content to the server. The server can analyze the historical input content within a preset time period to obtain a corresponding second personalized thesaurus. For example, the duration of the preset time period can be 60 days, and the historical input content of the user can be maintained according to this duration.

[0121] The server can provide the second personalized thesaurus to the client corresponding to the customer according to a preset cycle. For example, the preset cycle can be 30 days, so that the second personalized thesaurus can adapt to the changes in the long-term personalized needs of the user.

[0122] In the embodiments of the present invention, optionally, the above-mentioned second personalized thesaurus specifically includes at least one of the following entries:

[0123] Domain entries in the second target domain where the domain keywords match the historical input content;

[0124] Related entries that have a co-occurrence relationship with the historical input content;

[0125] Entries obtained based on the historical input content and the interest tree; and

[0126] Entries corresponding to the frequently used geographical locations.

[0127] Correspondingly, the embodiments of the present invention can provide the following determination methods for the second personalized thesaurus:

[0128] Determination method 1: Match the historical input content with domain keywords to obtain the second target domain corresponding to the matching domain keywords. For example, if the occupation of user B is "medicine", and a large number of words related to "medicine" are included in his historical input content, then the corresponding second target domain can be determined as "medicine", and personalized entries related to "medicine" can be recommended to him.

[0129] Determination method 2: Obtain the second personalized thesaurus based on the historical input content and the interest tree.

[0130] The interest tree includes a root node and sub-nodes representing user interests. The nodes in the interest tree represent categories, and the weight value of the node represents the degree of interest of the user in the category represented by the node; the leaf node refers to the smallest classification category in the interest tree, and the non-leaf node refers to the classification category with sub-classifications in the interest tree.

[0131] Embodiments of the present invention can utilize the hierarchical categories in the interest tree to refine the user's interests, determine the user's refined interests based on historical input content, and thus improve the accuracy of the second personalized thesaurus.

[0132] Determination method 3: Based on a corpus, obtain relevant entries that have a co-occurrence relationship with the historical input content. Co-occurrence can refer to co-occurring in a sentence or paragraph context. The co-occurrence relationship can include: the historical input content is adjacent to the relevant entry, or the historical input content is not adjacent to the relevant entry. Embodiments of the present invention can determine relevant entries with a co-occurrence probability exceeding a probability threshold from the relevant entries as personalized entries.

[0133] The above-mentioned corpus can include: input corpus in the input method environment, chat corpus in the instant messaging environment, corpus in the Weibo environment, corpus in the Q&A environment, etc.

[0134] It can be understood that those skilled in the art can adopt any one or a combination of determination methods 1 to 3 according to actual application requirements. For example, determination methods 1 and 3 can be combined and used. First, determine the domain entries in the second target domain according to determination method 1, and then screen the domain entries in the second target domain according to the co-occurrence probability.

[0135] Embodiments of the present invention provide the user with the second personalized thesaurus corresponding to the user status information, specifically including: downloading the second thesaurus file corresponding to the second personalized thesaurus from the server and loading the second thesaurus file locally to provide services to the user by using the loaded second thesaurus file.

[0136] In embodiments of the present invention, the second personalized thesaurus can include information such as input strings, personalized entries, tags, and word frequencies. Among them, the tag can represent the corresponding determination method. If a personalized entry with a tag is hit, the parameters of the corresponding determination method can be updated according to the corresponding hit information.

[0137] During the user's input process, according to the user's input string, a search can be performed in the second personalized thesaurus. If the search is successful, the corresponding personalized entry can be used as a candidate. For example, user B wants to input the target entry "Yas's syndrome" through the pinyin string "yasishizonghezheng", but "Yas's syndrome" does not exist in the traditional thesaurus. However, the second personalized thesaurus provided according to user B's input content includes "Yas's syndrome". Therefore, "Yas's syndrome" can be provided as a candidate according to the second personalized thesaurus. Since it can save the operation cost consumed by the selection and input of single characters, the input efficiency can be improved.

[0138] In an embodiment of the present invention, optionally, candidates may be sorted according to the priority of candidate types. The candidate types may include: user dictionary type, error correction type, system dictionary type, personalized dictionary type, cloud type, word formation type, etc.

[0139] Examples of the above priorities may include: user dictionary type > error correction type > system dictionary type & personalized dictionary type > cloud type > word formation type, etc. For example, the pinyin string "yasishizonghezheng" hits the second personalized dictionary but does not hit the user dictionary and the system dictionary, and there are no corresponding error correction candidates. Therefore, the candidate corresponding to the personalized entry "yasishizonghezheng" that is hit can be placed at the top of the candidates. It can be understood that the embodiments of the present invention do not limit the specific priorities.

[0140] In an embodiment of the present invention, optionally, the second personalized dictionary corresponds to a second time limit value. After the time limit corresponding to the second time limit value arrives, the second personalized dictionary can be cleared to release the space corresponding to the second personalized dictionary. The initial value of the second time limit value can be a duration such as 30 days.

[0141] It should be noted that if the subsequent input content of the user does not hit the first personalized dictionary and the second personalized dictionary, the user status information can be determined based on the subsequent input content to continuously provide the second personalized dictionary. Since the subsequent input content is not used for the statistics of the user status information when the subsequent input content hits the second personalized dictionary, the repeated provision of personalized entries can be avoided.

[0142] It can be understood that one or more second personalized dictionaries can be provided for the user on the terminal local of the embodiments of the present invention to provide corresponding personalized input services for the user. Among them, different second personalized dictionaries can be independent of each other. For example, the deletion of one second personalized dictionary does not affect another second personalized dictionary. Another example is that the hit of one second personalized dictionary does not affect another second personalized dictionary.

[0143] In summary, the method for processing the personalized dictionary in the embodiments of the present invention provides a second personalized dictionary that meets the long-term personalized needs of the user according to the historical input content input by the user within a preset time period.

[0144] The long-term personalized needs may include: professional needs, interest needs, etc. For example, if the profession of user B is "medicine", personalized entries related to medicine can be recommended to him. Another example is that if the interest characteristics of user C include "second dimension", personalized entries related to "second dimension" can be recommended to him.

[0145] Embodiments of the present invention can also recommend POI entries within the user's frequently used geographical locations to the user. The frequently used geographical locations specifically include: home or workplace, etc. The above POI entries specifically include: entries of merchants, communities, streets, etc. POIs around the frequently used geographical locations.

[0146] Method Embodiment Three

[0147] Referring to Figure 4 , a flowchart of the steps of Method Embodiment Three of a personalized thesaurus processing method according to the present invention is shown, which may specifically include the following steps:

[0148] Step 401, the client receives the input content; such as "bug net", "monkey", "tarantula island", etc.

[0149] Step 402, the client matches the input content with the feature entries. If the match is successful, the match count is incremented by 1;

[0150] Step 403, the client determines whether the match count is greater than the threshold. If so, the match count is cleared and a request is sent to the server;

[0151] Step 404, the server obtains the corresponding first personalized thesaurus for the request; for example, the first personalized thesaurus may include: personalized entries corresponding to the domain keyword "Animal Crossing", and related entries having a vector matching relationship with the input content;

[0152] Step 405, the client receives the first personalized thesaurus from the server and loads the first personalized thesaurus locally;

[0153] Step 406, the client provides candidates based on the user's input string and the first personalized thesaurus;

[0154] Step 407, the client determines whether the user's subsequent input content hits the first personalized thesaurus. If so, step 408 is executed; otherwise, step 409 is executed; the subsequent input content is also the candidate selected by the user.

[0155] Step 408, increase the first time limit value corresponding to the first personalized thesaurus;

[0156] Step 409, the client determines whether the user's subsequent input content hits the first personalized thesaurus. If not, the subsequent input content is input to step 402.

[0157] This embodiment can provide the user with the corresponding first personalized thesaurus that meets the user's real-time topic requirements according to the matching information between the user's input content and the feature entries.

[0158] Method Embodiment Four

[0159] Referring toFigure 5 shows a flowchart of the steps of the fourth embodiment of a method for processing a personalized word library according to the present invention, which may specifically include the following steps:

[0160] Step 501, the client sends the longitude and latitude information of the last three times to the server;

[0161] The latest longitude and latitude information can represent the latest obtained longitude and latitude information.

[0162] Step 502, the server determines whether the geographical location where the user is located has been updated according to the longitude and latitude information of the last three times. If so, it sends a first status value to the client;

[0163] The first status value represents that the geographical location where the user is located has been updated. It can be understood that the server can also send a second status value, and the second status value can represent that the geographical location where the user is located has not been updated.

[0164] Step 503, the client sends the latest longitude and latitude information to the server according to the first status value;

[0165] Step 504, the server determines the corresponding city word package according to the latest longitude and latitude information;

[0166] Step 505, the client loads the city word package locally;

[0167] Step 506, the client provides candidates according to the user's input string and the city word package;

[0168] Step 507, the client determines whether the subsequent input content of the user hits the city word package. If so, it increases the first time limit value corresponding to the city word package.

[0169] This embodiment can provide the user with the first personalized word library corresponding to the user's geographical word demand according to the update information of the geographical location where the user is located.

[0170] Method Embodiment Five

[0171] Refer to Figure 6 shows a flowchart of the steps of the fifth embodiment of a method for processing a personalized word library according to the present invention, which may specifically include the following steps:

[0172] Step 601, the server determines a set of users whose historical input content has a duration exceeding a preset number of days;

[0173] The preset number of days can be determined by those skilled in the art according to actual application requirements. For example, the preset number of days is 30 days. The client can upload the user's historical input content to the server in units of days.

[0174] Step 602: For the users in the user set, the server determines a corresponding second personalized thesaurus based on their historical input content and environmental characteristics.

[0175] The environmental characteristics include: location characteristics, APP (Application) characteristics, etc., which are used to assist in determining the user's interest characteristics. For example, if the APP characteristics corresponding to multiple historical input contents include "basketball", it can be considered that the user's interest characteristics include "basketball".

[0176] Step 603: The server sends the second personalized thesaurus to the client corresponding to the user according to a preset period.

[0177] Step 604: The client receives the second personalized thesaurus from the server and loads the second personalized thesaurus locally.

[0178] Step 605: The client provides candidates according to the user's input string and the second personalized thesaurus.

[0179] According to the historical input content input by the user within a preset time period, the embodiment of the present invention provides a second personalized thesaurus that meets the user's long-term personalized needs.

[0180] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of combinations of movement actions. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequence, 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 movement actions involved are not necessarily essential for the embodiments of the present invention.

[0181] Device embodiments

[0182] Refer to Figure 7 , which shows a structural block diagram of an embodiment of a processing device for a personalized thesaurus of the present invention, and specifically may include:

[0183] A user status information determination module 701, configured to determine user status information; the above user status information may include: matching information between the user's input content and feature entries, and / or updated information on the geographical location where the user is located; and

[0184] A first providing module 702, configured to provide a first personalized thesaurus corresponding to the above user status information to the user if the above user status information meets a preset condition.

[0185] Optionally, the above preset condition may include:

[0186] The number of input contents matching the feature entries exceeds the threshold; and / or

[0187] The geographical location where the user is located is updated.

[0188] Optionally, the above-mentioned feature entries may include at least one of the following entries: domain entries, self-created entries, and cloud entries.

[0189] Optionally, the above-mentioned first personalized thesaurus may include at least one of the following entries:

[0190] Domain entries within the first target domain where the domain keywords match the above-mentioned input content;

[0191] Related entries having a vector matching relationship with the above-mentioned input content;

[0192] Entries corresponding to the updated geographical location; and

[0193] Entries matching the above-mentioned input content and its context.

[0194] Optionally, the above-mentioned first providing module 702 may include:

[0195] A request sending module, configured to send a request to the server if a preset condition is met; the above-mentioned request may include: the above-mentioned user status information;

[0196] A thesaurus receiving module, configured to receive the first personalized thesaurus returned by the server according to the above-mentioned request.

[0197] Optionally, the above-mentioned first personalized thesaurus corresponds to a first expiration value, and the above-mentioned device may further include:

[0198] An increment module, configured to increment the first expiration value corresponding to the above-mentioned first personalized thesaurus if the subsequent input content of the user hits the above-mentioned first personalized thesaurus.

[0199] Optionally, the above-mentioned first personalized thesaurus corresponds to a first expiration value, and the above-mentioned device may further include:

[0200] A deletion module, configured to delete the above-mentioned first personalized thesaurus if the time corresponding to the above-mentioned first expiration value is reached.

[0201] Optionally, the above-mentioned device may further include:

[0202] A marker adding module, configured to add a feature entry marker to the local entries in the local thesaurus;

[0203] A matching module, configured to determine that the above-mentioned input content matches the feature entries if the local entries hit by the user's input content carry a feature entry marker.

[0204] Optionally, the above-mentioned device may further include:

[0205] A second providing module, configured to provide a second personalized word library to the user according to a preset period; the second personalized word library is obtained from the historical input content input by the user within a preset time period and / or the user's common geographical location.

[0206] Optionally, the second personalized word library may include at least one of the following entries:

[0207] Domain entries in a second target domain where the domain keywords match the above historical input content;

[0208] Related entries that have a co-occurrence relationship with the above historical input content;

[0209] Entries obtained based on the above historical input content and the interest tree; and

[0210] Entries corresponding to the above common geographical location.

[0211] Optionally, the above-mentioned device may further include:

[0212] The above user status information determination module 701 is further configured to determine user status information according to the subsequent input content of the user in the case where the subsequent input content of the user does not hit the first personalized word library and the second personalized word library.

[0213] Optionally, the type of the above geographical location may include at least one of the following types:

[0214] Administrative regions, communities, streets, and buildings.

[0215] For the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, please refer to the partial description of the method embodiments.

[0216] Each embodiment in this specification is described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, please refer to each other.

[0217] Regarding the device in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0218] An embodiment of the present invention provides an apparatus for processing a personalized word library, including a memory and one or more programs, where the one or more programs are stored in the memory and configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: determining user status information; the user status information includes: matching information between the user's input content and feature entries, and / or updated information on the geographical location where the user is located; if the user status information meets a preset condition, providing the user with a first personalized word library corresponding to the user status information.

[0219] Figure 8 FIG. 4 is a block diagram of an apparatus 800 for processing a personalized word library 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.

[0220] Referring to Figure 8 , the apparatus 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.

[0221] The processing component 802 generally controls the overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communication, camera operations, and recording operations. The processing element 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above 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.

[0222] The memory 804 is configured to store various types of data to support the operation of the device 800. Examples of such data include instructions for any application or method operating on the apparatus 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk.

[0223] The power supply component 806 provides power for 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.

[0224] The multimedia component 808 includes a screen that provides an output interface between the above-mentioned 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 can be implemented as a touch screen 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 above touch sensors can not only sense the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the above touch or swipe operations. 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 can receive external multimedia data. Each of the front camera and the rear camera can be a fixed optical lens system or have a focal length and optical zoom capabilities.

[0225] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), which is configured to receive external audio signals when the device 800 is in an operating mode, such as a call mode, a recording mode, and a voice input mode. The received audio signals can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

[0226] The I / O interface 812 provides an interface between the processing component 802 and a peripheral interface module, and the above peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

[0227] The sensor assembly 814 includes one or more sensors for providing an assessment of the status of the device 800 in various aspects. For example, the sensor assembly 814 can detect the on / off state of the device 800, the relative positioning of components, such as the display and keypad of the device 800 as described above. The sensor assembly 814 can also detect a change in the position 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 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0228] The communication component 816 is configured to facilitate communication between the device 800 and other devices in a wired or wireless manner. The device 800 can access a wireless network based on communication standards, 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 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0229] In an exemplary embodiment, the device 800 can 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 for performing the above method.

[0230] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as the memory 804 including instructions that can be executed by the processor 820 of the device 800 to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0231] Figure 9It is a schematic structural diagram of a server in some embodiments of the present invention. The server 1900 may vary greatly due to different configurations or performances, and may include one or more central processing units (CPUs) 1922 (for example, one or more processors) and a memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) for storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage media 1930 may be transient storage or persistent storage. The programs stored in the storage media 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Further, the central processing unit 1922 may be configured to communicate with the storage media 1930 and execute a series of instruction operations in the storage media 1930 on the server 1900.

[0232] The server 1900 may further include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input / 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, and so on.

[0233] A non-transitory computer-readable storage medium, when the instructions in the above storage medium are executed by a processor of a device (server or terminal), enables the device to execute Figures 2 to 6 the processing method of the personalized word library shown in any one of

[0234] A non-transitory computer-readable storage medium, when the instructions in the above storage medium are executed by a processor of a device (server or terminal), enables the device to execute a processing method of a personalized word library. The above method includes: determining user status information; the user status information includes: matching information between the user's input content and feature entries, and / or updated information on the geographical location where the user is located; if the user status information meets a preset condition, providing the user with the first personalized word library corresponding to the user status information.

[0235] Embodiments of the present invention disclose A1. A processing method of a personalized word library, the above method includes:

[0236] Determining user status information; the user status information includes: matching information between the user's input content and feature entries, and / or updated information on the geographical location of the domain where the user is located;

[0237] If the user status information meets the preset conditions, provide the user with the first personalized thesaurus corresponding to the user status information.

[0238] A2. According to the method described in A1, the preset conditions include:

[0239] The number of input contents matching the feature entries exceeds the threshold; and / or

[0240] The geographical location where the user is located is updated.

[0241] A3. According to the method described in A1, the feature entries include at least one of the following entries: domain entries, self-created entries, and cloud entries.

[0242] A4. According to the method described in A1, the first personalized thesaurus includes at least one of the following entries:

[0243] Domain entries in the first target domain where the domain keywords match the input content;

[0244] Related entries having a vector matching relationship with the input content;

[0245] Entries corresponding to the updated geographical location; and

[0246] Entries matching the input content and its context.

[0247] A5. According to the method described in any one of A1 to A4, providing the user with the first personalized thesaurus corresponding to the user status information includes:

[0248] If it meets the preset conditions, send a request to the server; the request includes: the user status information;

[0249] Receive the first personalized thesaurus returned by the server according to the request.

[0250] A6. According to the method described in any one of A1 to A4, the first personalized thesaurus corresponds to a first expiration value, and the method further includes:

[0251] If the subsequent input content of the user hits the first personalized thesaurus, increase the first expiration value corresponding to the first personalized thesaurus.

[0252] A7. According to the method described in any one of A1 to A4, the first personalized thesaurus corresponds to a first expiration value, and the method further includes:

[0253] If the time corresponding to the first expiration value is reached, delete the first personalized thesaurus.

[0254] A8. The method according to any one of A1 to A4, the method further comprising:

[0255] Adding a feature entry marker to the local entries in the local thesaurus;

[0256] If the local entry hit by the user's input content has a feature entry marker, then the input content matches the feature entry.

[0257] A9. The method according to any one of A1 to A4, the method further comprising:

[0258] Providing a second personalized thesaurus to the user according to a preset period; the second personalized thesaurus is obtained from the historical input content input by the user within a preset time period and / or the user's common geographical location.

[0259] A10. The method according to A9, the second personalized thesaurus includes at least one of the following entries:

[0260] Domain entries in the second target domain where the domain keywords match the historical input content;

[0261] Related entries having a co-occurrence relationship with the historical input content;

[0262] Entries obtained based on the historical input content and the interest tree; and

[0263] Entries corresponding to the common geographical location.

[0264] A11. The method according to any one of A1 to A4, the method further comprising:

[0265] If the subsequent input content of the user does not hit the first personalized thesaurus and the second personalized thesaurus, then determining the user status information according to the subsequent input content.

[0266] A12. The method according to any one of A1 to A4, the types of the geographical location include at least one of the following types:

[0267] Administrative region, community, street, and building.

[0268] Embodiment of the present invention discloses B13. A processing device for a personalized thesaurus, comprising:

[0269] A user status information determining module, configured to determine user status information; the user status information includes: matching information between the user's input content and the feature entry and / or updated information of the geographical location where the user is located; and

[0270] The first providing module is configured to provide the user with the first personalized thesaurus corresponding to the user status information if the user status information meets a preset condition.

[0271] B14. The device according to B13, wherein the preset condition includes:

[0272] The number of input contents matching the feature entries exceeds a threshold; and / or

[0273] The geographical location where the user is located is updated.

[0274] B15. The device according to B13, wherein the feature entries include at least one of the following entries: field entries, self-created entries, and cloud entries.

[0275] B16. The device according to B13, wherein the first personalized thesaurus includes at least one of the following entries:

[0276] Field entries in the first target field where the field keywords match the input content;

[0277] Related entries having a vector matching relationship with the input content;

[0278] Entries corresponding to the updated geographical location; and

[0279] Entries matching the input content and its context.

[0280] B17. The device according to any one of B13 to B16, wherein the first providing module includes:

[0281] A request sending module, configured to send a request to the server if the preset condition is met; the request includes: the user status information;

[0282] A thesaurus receiving module, configured to receive the first personalized thesaurus returned by the server according to the request.

[0283] B18. The device according to any one of B13 to B16, wherein the first personalized thesaurus corresponds to a first time limit value, and the device further includes:

[0284] An increment module, configured to increment the first time limit value corresponding to the first personalized thesaurus if the subsequent input content of the user hits the first personalized thesaurus.

[0285] B19. The device according to any one of B13 to B16, wherein the first personalized thesaurus corresponds to a first time limit value, and the device further includes:

[0286] A deletion module, configured to delete the first personalized thesaurus if the time corresponding to the first time limit value is reached.

[0287] B20. The device according to any one of B13 to B16, further comprising:

[0288] A tag adding module, configured to add feature entry tags to local entries in a local thesaurus;

[0289] A matching module, configured to determine that the input content matches a feature entry if the local entry hit by the user's input content has a feature entry tag.

[0290] B21. The device according to any one of B13 to B16, further comprising:

[0291] A second providing module, configured to provide a second personalized thesaurus to the user according to a preset period; the second personalized thesaurus is obtained from the historical input content input by the user within a preset time period and / or the user's common geographical location.

[0292] B22. The device according to B21, wherein the second personalized thesaurus comprises at least one of the following entries:

[0293] Domain entries in a second target domain where domain keywords match the historical input content;

[0294] Related entries having a co-occurrence relationship with the historical input content;

[0295] Entries obtained based on the historical input content and an interest tree; and

[0296] Entries corresponding to the common geographical location.

[0297] B23. The device according to any one of B13 to B16, further comprising:

[0298] The user status information determining module is further configured to determine user status information according to the subsequent input content in the case where the subsequent input content of the user does not hit the first personalized thesaurus and the second personalized thesaurus.

[0299] B24. The device according to any one of B13 to B16, wherein the type of the geographical location comprises at least one of the following types:

[0300] Administrative regions, communities, streets, and buildings.

[0301] Embodiments of the present invention disclose C25. A device for processing a personalized thesaurus, comprising a memory, and one or more programs, wherein one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include instructions for performing the following operations:

[0302] Determine user status information; the user status information includes: matching information between the input content of the user and feature entries, and / or updated information on the geographical location where the user is located;

[0303] If the user status information meets a preset condition, provide the user with a first personalized thesaurus corresponding to the user status information.

[0304] C26. The device according to C25, wherein the preset condition includes:

[0305] The number of input contents matching the feature entries exceeds a threshold; and / or

[0306] The geographical location where the user is located is updated.

[0307] C27. The device according to C25, wherein the feature entries include at least one of the following entries: field entries, self-created entries, and cloud entries.

[0308] C28. The device according to C25, wherein the first personalized thesaurus includes at least one of the following entries:

[0309] Field entries in the first target field where the field keywords match the input content;

[0310] Related entries having a vector matching relationship with the input content;

[0311] Entries corresponding to the updated geographical location; and

[0312] Entries matching the input content and its context.

[0313] C29. The device according to any one of C25 to C28, wherein providing the user with the first personalized thesaurus corresponding to the user status information includes:

[0314] If the preset condition is met, send a request to the server; the request includes: the user status information;

[0315] Receive the first personalized thesaurus returned by the server according to the request.

[0316] C30. The device according to any one of C25 to C28, wherein the first personalized thesaurus corresponds to a first time limit value, and the device is further configured to be executed by one or more processors for the one or more programs including instructions for performing the following operations:

[0317] If the subsequent input content of the user hits the first personalized thesaurus, increase the first time limit value corresponding to the first personalized thesaurus.

[0318] C31. The apparatus according to any one of C25 to C28, wherein the first personalized vocabulary corresponds to a first time limit value, and the apparatus further comprises:

[0319] If the time corresponding to the first time limit value is reached, the first personalized vocabulary is deleted.

[0320] C32. The apparatus according to any one of C25 to C28, wherein the apparatus is further configured to execute the one or more programs by one or more processors, and the one or more programs include instructions for performing the following operations:

[0321] Adding feature entry markers to local entries in the local vocabulary;

[0322] If the local entry hit by the user's input content has a feature entry marker, the input content matches the feature entry.

[0323] C33. The apparatus according to any one of C25 to C28, wherein the apparatus is further configured to execute the one or more programs by one or more processors, and the one or more programs include instructions for performing the following operations:

[0324] Providing a second personalized vocabulary to the user according to a preset period; the second personalized vocabulary is obtained from the historical input content input by the user within a preset time period and / or the user's common geographical locations.

[0325] C34. The apparatus according to C33, wherein the second personalized vocabulary includes at least one of the following entries:

[0326] Domain entries in a second target domain where domain keywords match the historical input content;

[0327] Related entries having a co-occurrence relationship with the historical input content;

[0328] Entries obtained based on the historical input content and the interest tree; and

[0329] Entries corresponding to the common geographical locations.

[0330] C35. The apparatus according to any one of C25 to C28, wherein the apparatus is further configured to execute the one or more programs by one or more processors, and the one or more programs include instructions for performing the following operations:

[0331] If the subsequent input content of the user does not hit the first personalized vocabulary and the second personalized vocabulary, the user status information is determined according to the subsequent input content.

[0332] C36. The apparatus according to any one of C25 to C28, wherein the types of the geographical locations include at least one of the following types:

[0333] Administrative regions, communities, streets, and buildings.

[0334] An embodiment of the present invention discloses D37, a machine-readable medium having instructions stored thereon, which when executed by one or more processors cause the apparatus to perform the processing method of the personalized thesaurus as described in one or more of A1 to A12.

[0335] Those skilled in the art will readily conceive of other embodiments of the present 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 known common knowledge or conventional technical means in the technical field not disclosed in this disclosure. The specification and examples are only to be considered exemplary, and the true scope and spirit of the present invention are pointed out by the following claims.

[0336] It should be understood that the present invention is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

[0337] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0338] The above provides a detailed introduction to a processing method for a personalized thesaurus, a processing device for a personalized thesaurus, and a device for processing a personalized thesaurus provided by the present invention. Specific examples are used herein to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for processing a personalized thesaurus, characterized in that, The method includes: Determine user status information, where the user status information is real-time information during the user's use of the device; the user status information includes: matching information between the user's input content and feature entries and updated information on the domain geographical location where the user is located; If the user status information meets the preset conditions, provide the user with a first personalized thesaurus corresponding to the user status information; The user's input content is an input string in the input method program; The first personalized thesaurus includes at least one of the following entries: Domain entries in the first target domain where the domain keywords match the input content; Related entries that have a vector matching relationship with the input content; Entries corresponding to the updated geographical location; and Entries that match the input content and its context; The first personalized thesaurus corresponds to a first time limit value, and the method further includes: If the user's subsequent input content hits the first personalized thesaurus, increase the first time limit value corresponding to the first personalized thesaurus; If the time corresponding to the first time limit value is reached, delete the first personalized thesaurus; The related entries that have a vector matching relationship with the input content include: The input content can be converted into a first word vector including multiple dimensions, and each dimension of the first word vector has a specific meaning; the multiple first word vectors are fused into a new first word vector; the new first word vector obtains a matching second word vector according to the vector matching relationship, and the entry corresponding to the second word vector is used as the related entry.

2. The method according to claim 1, characterized in that, The preset conditions include: The number of input contents matching the feature entries exceeds the threshold and the geographical location where the user is located is updated.

3. The method according to claim 1, characterized in that, The feature entries include at least one of the following entries: domain entries, self-created entries, and cloud entries.

4. The method according to any one of claims 1 to 3, characterized in that, The providing the user with the first personalized thesaurus corresponding to the user status information includes: If the preset conditions are met, send a request to the server; the request includes: the user status information; Receive the first personalized thesaurus returned by the server according to the request.

5. A device for processing a personalized thesaurus, characterized in that, It includes: A user status information determination module for determining user status information, where the user status information is real-time information during the user's use of the device; The user status information includes: matching information between the user's input content and feature entries and updated information on the geographical location where the user is located; and A first providing module for providing the user with a first personalized thesaurus corresponding to the user status information if the user status information meets the preset conditions; The user's input content is an input string in the input method program; The first personalized thesaurus includes at least one of the following entries: Domain entries in the first target domain where the domain keywords match the input content; Related entries that have a vector matching relationship with the input content; Entries corresponding to the updated geographical location; and Entries that match the input content and its context; The first personalized thesaurus corresponds to a first time limit value, and the device is also used for: If the subsequent input content of the user hits the first personalized thesaurus, increase the first time limit value corresponding to the first personalized thesaurus; If the time corresponding to the first time limit value is reached, delete the first personalized thesaurus; The relevant entries having a vector matching relationship with the input content include: The input content can be converted into a first word vector including multiple dimensions, and each dimension of the first word vector has a specific meaning; the multiple first word vectors are fused into a new first word vector; the new first word vector obtains a matching second word vector according to the vector matching relationship, and the entry corresponding to the second word vector is used as the relevant entry.

6. An apparatus for processing a personalized thesaurus, characterized in that It includes a memory and one or more programs, where 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: Determine user status information, where the user status information is real-time information during the user's use of the device; the user status information includes: matching information between the user's input content and feature entries and updated information on the geographical location where the user is located; If the user status information meets the preset conditions, provide the user with the first personalized thesaurus corresponding to the user status information; The input content of the user is an input string in the input method program; The first personalized thesaurus includes at least one of the following entries: Domain entries in the first target domain where the domain keywords match the input content; Relevant entries having a vector matching relationship with the input content; Entries corresponding to the updated geographical location; and Entries matching the input content and its context; The first personalized thesaurus corresponds to a first time limit value, and the device is further configured to: If the subsequent input content of the user hits the first personalized thesaurus, increase the first time limit value corresponding to the first personalized thesaurus; If the time corresponding to the first time limit value is reached, delete the first personalized thesaurus; The relevant entries having a vector matching relationship with the input content include: The input content can be converted into a first word vector including multiple dimensions, and each dimension of the first word vector has a specific meaning; the multiple first word vectors are fused into a new first word vector; the new first word vector obtains a matching second word vector according to the vector matching relationship, and the entry corresponding to the second word vector is used as the relevant entry.

7. A machine-readable medium having instructions stored thereon that, when executed by one or more processors, cause the apparatus to perform the method for processing a personalized thesaurus according to one or more of claims 1 to 4.

Images