CN111984132B - Method and system for inputting information according to context environment - Google Patents
Method and system for inputting information according to context environment Download PDFInfo
- Publication number
- CN111984132B CN111984132B CN202010646972.3A CN202010646972A CN111984132B CN 111984132 B CN111984132 B CN 111984132B CN 202010646972 A CN202010646972 A CN 202010646972A CN 111984132 B CN111984132 B CN 111984132B
- Authority
- CN
- China
- Prior art keywords
- word
- words
- input
- candidate
- information queue
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0236—Character input methods using selection techniques to select from displayed items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/109—Font handling; Temporal or kinetic typography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Probability & Statistics with Applications (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a method and a system for inputting information according to context environment, wherein the weighting method comprises the following steps: establishing an information queue for each of a plurality of applications, storing an input message and a received message associated with each application in the information queue, respectively; determining the input times of each input word and the receiving times of each received word; selecting at least two input words from the plurality of input words according to the input times to be used as standard words, and using a word set associated with each standard word as a basic word set; determining words existing in the input message and the received message at the same time as public words, and determining a plurality of weighted words based on the receiving times and the input times of each public word; and carrying out weighted calculation on the matching degree of each candidate word and each weight word to determine the priority level of each candidate word, sequencing a plurality of candidate words according to the priority level, and providing the candidate words according to the sequencing order.
Description
Technical Field
The present invention relates to the field of information technology, and more particularly, to a method and system for inputting information according to a context environment.
Background
At present, with the continuous progress of internet technology and the continuous improvement of mobile terminal performance, mobile terminals have more and more functions. Generally, an information input function is a very important function in a mobile terminal. For example, the information input function may be used for an instant messenger application, a shopping application, a document processing application, and the like within the mobile terminal. Because of the need to be frequently used, information input functions are also placing greater expectations such as rapidity, accuracy, efficiency, etc. of input.
In the prior art, when a user wishes to input information through a mobile terminal, some characters are generally required to be input, and an information input application in the mobile terminal determines a plurality of words according to the characters and provides or presents the words for the user to select. However, in the related art, the order of the plurality of words is generally determined based on a fixed order or an input habit of the user, and cannot be determined according to a context of an information input being performed by the user.
Disclosure of Invention
According to an aspect of the present invention, there is provided a method for information input according to a context, the method including:
establishing an information queue for each of a plurality of applications, storing an input message and a received message associated with each application in the information queue, respectively;
monitoring a first quantity of respective input messages and a second quantity of received messages in each information queue in real time, when the first quantity of the input messages of a specific information queue is larger than a quantity threshold value, determining whether the ratio of the second quantity to the first quantity of the specific information queue is within a preset range, and if so, counting the times of each input word in a plurality of input words in the input messages of the specific information queue to determine the input times of each input word;
selecting at least two input words from the plurality of input words according to the input times to be used as standard words, and using a word set associated with each standard word as a basic word set;
counting the times of receiving each receiving word in a plurality of receiving words in the receiving message of the specific information queue to determine the receiving times of each receiving word;
determining words existing in the input message and the received message at the same time as public words, determining an importance coefficient of each public word based on the receiving times and the input times of each public word, and selecting the public words with the importance coefficients larger than a threshold value as weighted words to determine a plurality of weighted words;
when characters input by a user are received, a plurality of candidate words corresponding to the characters are obtained from a plurality of basic word sets, the matching degree of each candidate word and each weight word in a plurality of weight words is calculated, the matching degree of each candidate word and each weight word is weighted and calculated to determine the priority level of each candidate word, the candidate words are ranked based on the priority level of each candidate word, and the candidate words are provided according to the ranking order.
Wherein the application is an instant messaging application, a financial application, or a gaming application.
Storing the incoming messages and the received messages associated with each application in an information queue, respectively, comprises:
the input messages associated with each application are stored in an input portion of the information queue and the input messages associated with each application are stored in an output portion of the information queue.
Monitoring, in real-time, the respective first number of incoming messages and the second number of received messages in each of the information queues includes:
monitoring a first number of all characters included in an input message in an input part of an information queue in real time; and monitoring in real time a second number of all characters comprised by the output message in the output portion of the information queue.
Further comprising setting a respective quantity threshold for each application.
And setting respective preset ranges for each application.
Selecting at least two input words from the plurality of input words as standard words according to the number of inputs includes:
determining a number of inputs C for each of a plurality of input termsp;
Sorting the plurality of input words according to the descending order of the input times to obtain a word list;
determining input words ranked before a preset position in the word list as candidate input words;
calculating the matching degree of each candidate input word and the description file of the affiliated application;
and determining the candidate input words with the matching degrees larger than the threshold value as the basic words.
Before the information queue is established for each of the plurality of applications, dividing all terms used for information input into a plurality of term sets according to the category information, wherein each term set comprises a plurality of terms and each term set has a respective category name.
Taking the set of words associated with each standard word as a base set of words includes: a set of terms in the plurality of sets of terms associated with the at least one standard term is selected as a base set of terms.
The determining the importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word includes:
determining the number of receptions CO of each common termy;
Determining the number of inputs CI for each common termy;
Where y is a natural number and 1. ltoreq. y.ltoreq.No, where No is the number of common words.
The threshold is 1, 0.9, 0.8, 0.6, or 0.5.
When receiving a character input by a user, acquiring a plurality of words to be selected corresponding to the character from a plurality of basic word sets comprises:
converting the received characters input by the user into retrieval conditions;
searching in each basic word set in the plurality of basic word sets based on the searching conditions to obtain a plurality of searched words;
and taking the plurality of searched words as a plurality of words to be selected corresponding to the characters.
Calculating a degree of matching of each candidate term to each weighted term in the plurality of weighted terms comprises:
and semantically matching each candidate word with each weight word in the plurality of weight words, and taking the matching degree of the semantic matching as the matching degree of each candidate word with each weight word in the plurality of weight words.
Performing a weighted calculation on the matching degree of each candidate word and each weighted word to determine the priority level of each candidate word comprises:
determining the matching degree M of the ith candidate word and the jth weight wordij;
Determining the weight coefficient Ow of the jth weight wordj;
Based on matching degree M of ith candidate word and jth weight wordijCalculating the priority P of the ith candidate wordi=Mi1×Ow1+Mi2×Ow2+…+Mij×Owj;
Where i and j are natural numbers and 1 ≦ i ≦ N1, 1 ≦ j ≦ N2, N1 is the number of candidate words, and N2 is the number of weighted words.
Ranking the plurality of candidate words based on the priority level of each candidate word and providing the plurality of candidate words in a ranked order comprises:
sorting the plurality of candidate words based on a descending order of priority of each candidate word to generate a candidate word list;
dividing the candidate word list into a plurality of candidate word groups with descending priority;
sequentially providing the candidate word groups according to the descending order of priority;
wherein all candidate words in each candidate word group are provided in a random order;
wherein the priority of any one candidate word in the previous candidate word group is greater than the priority of each candidate word in the next candidate word group.
According to another aspect of the present invention, there is provided a system for information input according to a context, the system comprising:
the initialization device establishes an information queue for each application in a plurality of applications and respectively stores input messages and received messages associated with each application in the information queue;
the monitoring device monitors the first number of the input messages and the second number of the received messages in each information queue in real time, when the first number of the input messages of the specific information queue is larger than a number threshold value, whether the ratio of the second number to the first number of the specific information queue is within a preset range is determined, and if the ratio is within the preset range, the frequency statistics is carried out on each input word in a plurality of input words in the input messages of the specific information queue so as to determine the input frequency of each input word;
a selection device which selects at least two input words from the plurality of input words as standard words according to the input times, and takes a word set associated with each standard word as a basic word set;
a counting device for counting the times of receiving each of a plurality of receiving words in the receiving message of the specific information queue to determine the receiving times of each receiving word;
a determining device that determines words existing in both the input message and the received message as common words, determines an importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word, and selects the common words having the importance coefficients larger than a threshold value as weight words to determine a plurality of weight words;
the device comprises a providing device, a first obtaining device and a second obtaining device, wherein the first obtaining device is used for obtaining a plurality of candidate words corresponding to characters from a plurality of basic word sets when the characters input by a user are received, calculating the matching degree of each candidate word and each weight word in a plurality of weight words, carrying out weighted calculation on the matching degree of each candidate word and each weight word to determine the priority level of each candidate word, sequencing the candidate words based on the priority level of each candidate word, and providing the candidate words according to the sequencing order.
Wherein the application is an instant messaging application, a financial application, or a gaming application.
The initializing means stores the input message and the received message associated with each application in an information queue respectively includes:
the initialization means stores the input messages associated with each application in an input portion of the information queue and stores the input messages associated with each application in an output portion of the information queue.
The monitoring device for monitoring the first number of input messages and the second number of received messages in each information queue in real time comprises the following steps:
the monitoring device monitors a first number of all characters included in an input message in an input part of the information queue in real time; and monitoring in real time a second number of all characters comprised by the output message in the output portion of the information queue.
Further comprising setting a respective quantity threshold for each application.
And setting respective preset ranges for each application.
The selecting means selects at least two input words from the plurality of input words as standard words according to the number of inputs including:
the selection means determines the number of inputs C for each of the plurality of input wordsp;
The selection device sorts a plurality of input words according to the descending order of the input times to obtain a word list;
the selection device determines the input words ranked before the preset position in the word list as candidate input words;
the selection device calculates the matching degree of each candidate input word and the description file of the belonged application;
the selection means determines the candidate input word having the matching degree greater than a threshold as the base word.
The initialization device divides all words for information input into a plurality of word sets according to category information, wherein each word set comprises a plurality of words and each word set has a respective category name.
The selecting means includes, as a base word set, a word set associated with each standard word: the selection means selects a set of words from the plurality of sets of words associated with the at least one standard word as a base set of words.
The determining means determining the importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word includes:
the determining means determines the number of receptions CO of each common wordy;
The determining means determines the number of times of input of each common wordDigital CIy;
Where y is a natural number and 1. ltoreq. y.ltoreq.No, where No is the number of common words.
The threshold is 1, 0.9, 0.8, 0.6, or 0.5.
When receiving a character input by a user, the providing device acquires a plurality of words to be selected corresponding to the character from a plurality of basic word sets, wherein the words to be selected comprise:
the providing device converts the received characters input by the user into retrieval conditions;
the providing device searches in each basic word set in the plurality of basic word sets based on the search condition to obtain a plurality of searched words;
the providing device takes the plurality of searched words as a plurality of candidate words corresponding to the characters.
The providing device calculating the matching degree of each candidate word and each weighted word in the plurality of weighted words comprises the following steps:
the providing device semantically matches each candidate word with each of the plurality of weighted words, and takes a matching degree of the semantic matching as a matching degree of each candidate word with each of the plurality of weighted words.
The providing device performs weighted calculation on the matching degree of each candidate word and each weighted word to determine the priority level of each candidate word, and comprises the following steps:
the providing device determines the matching degree M of the ith candidate word and the jth weight wordij;
The providing device determines a weight coefficient Ow of the jth weighted wordj;
The providing device is based on the matching degree M of the ith candidate word and the jth weight wordijCalculating the priority P of the ith candidate wordi=Mi1×Ow1+Mi2×Ow2+…+Mij×Owj;
Where i and j are natural numbers and 1 ≦ i ≦ N1, 1 ≦ j ≦ N2, N1 is the number of candidate words, and N2 is the number of weighted words.
The providing means ranks the plurality of candidate words based on the priority level of each candidate word, and providing the plurality of candidate words in the ranked order comprises:
the providing device sorts a plurality of candidate words based on a descending order of priority of each candidate word to generate a candidate word list;
the providing means divides the candidate word list into a plurality of candidate word groups having descending order of priority;
the providing device sequentially provides the candidate word groups according to the descending order of priority;
wherein all candidate words in each candidate word group are provided in a random order;
wherein the priority of any one candidate word in the previous candidate word group is greater than the priority of each candidate word in the next candidate word group.
Drawings
A more complete understanding of exemplary embodiments of the present invention may be had by reference to the following drawings in which:
FIG. 1 is a flow chart of a method for information input based on contextual environment in accordance with the present invention;
FIG. 2 is a schematic diagram of information input according to a context in accordance with the present invention;
fig. 3 is a schematic structural diagram of a system for information input according to a context according to the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
FIG. 1 is a flow diagram of a method 100 for information input based on contextual environment in accordance with the present invention. The method 100 determines a number of inputs of each input term and a number of receptions of each received term when a first number of input messages of a particular information queue is greater than a number threshold, selects at least two input terms from a plurality of input terms as standard terms according to the number of inputs, and takes a term set associated with each standard term as a base term set. The method 100 determines words existing in both the input message and the received message as common words, and selects common words having an importance coefficient greater than a threshold value as weighted words to determine a plurality of weighted words. When a user input character is received, the method 100 obtains a plurality of candidate words corresponding to the character from a plurality of basic word sets, calculates a matching degree of each candidate word with each weighted word in a plurality of weighted words, performs weighted calculation on the matching degree of each candidate word with each weighted word to determine a priority level of each candidate word, ranks the plurality of candidate words based on the priority level of each candidate word, and provides the plurality of candidate words according to the ranked order.
The method 100 begins at step 101. In step 101, an information queue is established for each of a plurality of applications, and an incoming message and a received message associated with each application are stored in the information queue, respectively. Wherein the application may be of various types requiring message input and/or message output. The application may be an instant messaging applicationFinancial applications, gaming applications, multimedia applications, and the like. Storing the input message and the received message associated with each application in an information queue, respectively, comprises: the input messages associated with each application are stored in the input portion of the information queue and the input messages associated with each application are stored in the output portion of the information queue, as shown in fig. 2. Fig. 2 is a diagram illustrating information input according to a context according to the present invention. The input part of the information queue stores input messages 1, 2, 3, … …, Ini-1、IniAnd the output part of the information queue stores the output messages 1, 2, 3, … …, Outj-1、Outj. Where i and j are the number of incoming and outgoing messages, respectively. For this reason, the present invention needs to distinguish the information queue into an input part and an output part, wherein the input part and the output part can be respectively arranged at both ends of the information queue. When an input message associated with application a is received, the input message is stored to an input portion of the information queue of application a, and when an output message associated with application a is received, the input message is stored to an output portion of the information queue of application a.
Before the information queue is established for each of the plurality of applications, all terms used for information input are divided into a plurality of term sets according to the category information, wherein each term set comprises a plurality of terms and each term set has a respective category name. The category information is, for example, sports, music, history, and the like. The category information may also be basketball, football, volleyball, etc. The classification of all the words used for information input into a plurality of word sets according to the category information is, for example, a classification of all the words into a plurality of word sets according to the category to which each word belongs. Wherein at least one word belongs to multiple sets of words simultaneously. For example, the word "out of bounds" may belong to the information sets "basketball", "football" and "volleyball" simultaneously.
In step 102, monitoring a first number of respective input messages and a second number of received messages in each information queue in real time, when the first number of input messages of a specific information queue is larger than a number threshold, determining whether a ratio of the second number to the first number of the specific information queue is within a preset range, and if so, counting the number of times of each input word in a plurality of input words in the input messages of the specific information queue to determine the input number of times of each input word. For example, the number of times of input of each input word may be determined by counting the number of times of each input word in the plurality of input words by setting a counter for each input word.
Wherein the first number of input messages may refer to a number of characters included in the input messages and the second number of received messages may refer to a number of characters included in the received messages. To this end, monitoring in real-time a respective first number of incoming messages and a second number of received messages in each of the information queues comprises: monitoring a first number of all characters included in an input message in an input part of an information queue in real time; and monitoring in real time a second number of all characters comprised by the output message in the output portion of the information queue. The invention may set a respective number threshold for each application. For example, the number threshold set for the game application is 500 characters, 800 characters, 1000 characters, 1500 characters, or the like. The present invention sets a respective preset range for each application. For example, the predetermined range of the ratio of the second number to the first number of information queues is 50%, 80%, 100%, 150%, 200%, etc.
At step 103, at least two input terms are selected from the plurality of input terms as standard terms according to the number of inputs, and a term set associated with each standard term is used as a base term set. Wherein selecting at least two input terms from the plurality of input terms as the standard terms according to the number of inputs includes: determining a number of inputs C for each of a plurality of input termsp(ii) a Sorting the plurality of input words according to the descending order of the input times to obtain a word list; determining input words ranked before a preset position in the word list as candidate input words; calculating the matching degree of each candidate input word and the description file of the affiliated application; inputting candidate words with matching degree larger than matching thresholdThe base word is determined. Wherein C ispIs the number of inputs of the p-th input word and p is a natural number. Where 1 ≦ p ≦ Nw, and Nw is the number of input words. Wherein the matching threshold is for example 60%, 70%, 80%, etc. And determining the input word ranked before the preset position in the word list as a candidate input word. For example, when the number of input words is 200, input words ordered before 50 bits (including 50 bits), 100 bits (including 100 bits), or 150 bits (including 150 bits) in the word list are determined as candidate input words. The calculating the matching degree between each candidate input word and the description file of the attributed application is, for example, calculating the semantic matching degree, the content matching degree or the keyword matching degree between each candidate input word and the description file of the attributed application. The degree of matching is at least 0% and at most 100%. The matching threshold is, for example, 60%, 70%, 80%, etc. Further, taking the set of words associated with each standard word as the base set of words includes: a set of terms in the plurality of sets of terms associated with the at least one standard term is selected as a base set of terms. A particular set of terms may be associated with multiple standard terms. In general, whether a standard word is associated with a set of words is determined by determining the degree of association or matching of the standard word to descriptive information, characteristic information, etc. of the set of words. For example, a word set having a degree of association or matching with a particular standard word greater than a particular threshold is a base word set.
At step 104, a count of the number of times each received term of the plurality of received terms within the received message for the particular information queue is made to determine the number of times each received term is received. For example, the number of times of reception of each received word may be determined by counting the number of times of each received word in the plurality of received words by setting a counter for each received word.
In step 105, words existing in both the input message and the received message are determined as common words, i.e., words that are both the input word and the output word, as shown in fig. 2. Determining an importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word, and selecting the common words having the importance coefficients greater than a threshold value as weighted words to determineA plurality of weighted words, as shown in fig. 2. The determining the importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word includes: determining the number of receptions CO of each common termy(ii) a Determining the number of inputs CI for each common termy(ii) a Calculating a weight coefficient for each common term
Where y is a natural number and 1. ltoreq. y.ltoreq.No, where No is the number of common words. The threshold may be any reasonable value, such as 1, 0.9, 0.8, 0.6, or 0.5.
In step 106, when the user input characters are received, a plurality of candidate words corresponding to the characters are obtained from a plurality of basic word sets, the matching degree of each candidate word and each weight word in a plurality of weight words is calculated, the matching degree of each candidate word and each weight word is weighted to determine the priority level of each candidate word, the candidate words are ranked based on the priority level of each candidate word, and the candidate words are provided according to the ranking order.
When receiving a character input by a user, acquiring a plurality of words to be selected corresponding to the character from a plurality of basic word sets comprises: converting the received characters input by the user into retrieval conditions; searching in each basic word set in the plurality of basic word sets based on the searching conditions to obtain a plurality of searched words; and taking the plurality of searched words as a plurality of words to be selected corresponding to the characters.
Calculating a degree of matching of each candidate term to each weighted term in the plurality of weighted terms comprises: and semantically matching each candidate word with each weight word in the plurality of weight words, and taking the matching degree of the semantic matching as the matching degree of each candidate word with each weight word in the plurality of weight words. Performing a weighted calculation on the matching degree of each candidate word and each weighted word to determine the priority level of each candidate word comprises: determining the matching degree M of the ith candidate word and the jth weight wordij(ii) a Determining the weight coefficient Ow of the jth weight wordj(ii) a Based on matching degree M of ith candidate word and jth weight wordijCalculating the priority P of the ith candidate wordi=Mi1×Ow1+Mi2×Ow2+…+Mij×Owj. Where i and j are natural numbers and 1 ≦ i ≦ N1, 1 ≦ j ≦ N2, N1 is the number of candidate words, and N2 is the number of weighted words.
Ranking the plurality of candidate words based on the priority level of each candidate word and providing the plurality of candidate words in a ranked order comprises: sorting the plurality of candidate words based on a descending order of priority of each candidate word to generate a candidate word list; dividing the candidate word list into a plurality of candidate word groups with descending priority; sequentially providing the candidate word groups according to the descending order of priority; wherein all candidate words in each candidate word group are provided in a random order; wherein the priority of any one candidate word in the previous candidate word group is greater than the priority of each candidate word in the next candidate word group. A set of candidate word groups that ranks a plurality of candidate words in descending order of priority is shown in fig. 2.
Fig. 3 is a schematic diagram of a system 300 for information input according to a context according to the present invention. When the first number of input messages for the particular information queue is greater than the number threshold, the system 300 determines a number of inputs per input term and a number of receptions per received term, selects at least two input terms from the plurality of input terms as standard terms according to the number of inputs, and takes a set of terms associated with each standard term as a base set of terms. The system 300 determines words existing in both the input message and the received message as common words, and selects common words having an importance coefficient greater than a threshold value as weighted words to determine a plurality of weighted words. When the user input characters are received, the system 300 obtains a plurality of candidate words corresponding to the characters from a plurality of basic word sets, calculates a matching degree of each candidate word with each weighted word in a plurality of weighted words, performs weighted calculation on the matching degree of each candidate word with each weighted word to determine a priority level of each candidate word, ranks the candidate words based on the priority level of each candidate word, and provides the candidate words according to the ranked order.
The system 300 includes: initialization means 301, monitoring means 302, selection means 303, statistical means 304, determination means 305 and providing means 306. The initialization apparatus 301 establishes an information queue for each of a plurality of applications, and stores an input message and a received message associated with each application in the information queue, respectively. Wherein the application is an instant messaging application, a financial application, or a gaming application. The initializing means 301 stores the input message and the received message associated with each application in the information queue respectively includes: the initialization apparatus 301 stores the input message associated with each application in the input portion of the information queue and stores the input message associated with each application in the output portion of the information queue. The initialization apparatus 301 divides all words for information input into a plurality of word sets according to category information, wherein each word set includes a plurality of words and each word set has a respective category name.
The monitoring device 302 monitors a first number of respective input messages and a second number of received messages in each information queue in real time, determines whether a ratio of the second number to the first number of a specific information queue is within a preset range when the first number of input messages of the specific information queue is greater than a number threshold, and performs frequency statistics on each input word of a plurality of input words in the input messages of the specific information queue to determine the input frequency of each input word if the ratio is within the preset range. The monitoring means 302 monitoring in real-time the respective first number of incoming messages and the second number of received messages in each message queue comprises: the monitoring means 302 monitors in real time a first number of all characters comprised by the input message in the input part of the information queue; and monitoring in real time a second number of all characters comprised by the output message in the output portion of the information queue. The invention also includes setting a respective quantity threshold for each application and setting a respective preset range for each application.
The selection means 303 selects at least two input words from the plurality of input words as standard words according to the number of inputs, and takes the word set associated with each standard word as a base word set. The selecting means 303 selects at least two input words from the plurality of input words as the standard words according to the number of inputs including: the selection means 303 determines the number of inputs C for each of the plurality of input wordsp(ii) a The selecting device 303 sorts the plurality of input terms in descending order of the input times to obtain a term list; the selection means 303 determines an input word ranked before a predetermined position in the word list as a candidate input word; the selecting device 303 calculates the matching degree of each candidate input word and the description file of the belonged application; the selection means 303 determines the candidate input word having the matching degree greater than the threshold value as the base word. The selecting means 303 includes, as the base word set, the word set associated with each standard word: the selection means selects a set of words from the plurality of sets of words associated with the at least one standard word as a base set of words.
Statistics means 304 performs count statistics on the number of times each of the plurality of received words within the received message of the specific information queue to determine the number of times each received word is received.
The determination means 305 determines words existing in both the input message and the received message as common words, determines an importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word, and selects the common words having the importance coefficients larger than a threshold value as weighted words to determine a plurality of weighted words. The determination means 305 determining the importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word includes: the determining means 305 determines the number of receptions CO of each common wordy(ii) a The determination means 305 determines the number of inputs CI for each common termy(ii) a Determining means 305 calculates a weight coefficient for each common word
Where y is a natural number and 1. ltoreq. y.ltoreq.No, where No is the number of common words. The threshold may be 1, 0.9, 0.8, 0.6, or 0.5.
Providing device 306 obtains a plurality of candidate words corresponding to the characters from a plurality of basic word sets when receiving the characters input by the user, calculates a matching degree of each candidate word with each weighted word in a plurality of weighted words, performs weighted calculation on the matching degree of each candidate word with each weighted word to determine a priority level of each candidate word, ranks the candidate words based on the priority level of each candidate word, and provides the candidate words in the ranked order.
When receiving a character input by a user, providing device 306 obtains a plurality of candidate words corresponding to the character from a plurality of basic word sets, including: the providing device 306 converts the received characters input by the user into retrieval conditions; providing means 306 performs a search in each of the plurality of basic term sets based on the search condition to obtain a plurality of searched terms; providing device 306 takes the retrieved plurality of words as a plurality of candidate words corresponding to the characters.
Providing device 306 calculates a degree of matching of each candidate term with each weighted term in the plurality of weighted terms, including: providing means 306 semantically matches each candidate word with each weighted word of the plurality of weighted words, and takes a matching degree of the semantic matching as a matching degree of each candidate word with each weighted word of the plurality of weighted words.
Providing device 306 performs weighted calculation on the matching degree of each candidate word and each weighted word to determine the priority level of each candidate word, including: providing device 306 determines matching degree M of ith candidate word and jth weight wordij(ii) a Providing device 306 determines weight coefficient Ow of jth weighted wordj(ii) a Providing device 306 matches M with jth weight word based on ith candidate wordijCalculating the priority P of the ith candidate wordi=Mi1×Ow1+Mi2×Ow2+…+Mij×Owj;
Where i and j are natural numbers and 1 ≦ i ≦ N1, 1 ≦ j ≦ N2, N1 is the number of candidate words, and N2 is the number of weighted words.
Providing device 306 ranks the plurality of candidate words based on the priority level of each candidate word, and provides the plurality of candidate words in the ranked order, including: providing device 306 sorts the plurality of candidate words based on the descending order of priority of each candidate word to generate a candidate word list; providing device 306 divides the candidate word list into a plurality of candidate word groups with descending order of priority; providing means 306 sequentially provides the plurality of candidate word groups in descending order of priority; wherein all candidate words in each candidate word group are provided in a random order; wherein the priority of any one candidate word in the previous candidate word group is greater than the priority of each candidate word in the next candidate word group.
The invention has been described with reference to a few embodiments. However, other embodiments of the invention than the one disclosed above are equally possible within the scope of the invention, as would be apparent to a person skilled in the art from the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the [ device, component, etc ]" are to be interpreted openly as referring to at least one instance of said device, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
Claims (10)
1. A method of information input according to a contextual environment, the method comprising:
establishing an information queue for each of a plurality of applications, storing an input message and a received message associated with each application in the information queue, respectively;
monitoring a first quantity of respective input messages and a second quantity of received messages in each information queue in real time, when the first quantity of the input messages of a specific information queue is larger than a quantity threshold value, determining whether the ratio of the second quantity to the first quantity of the specific information queue is within a preset range, and if so, counting the times of each input word in a plurality of input words in the input messages of the specific information queue to determine the input times of each input word;
selecting at least two input words from the plurality of input words according to the input times to be used as standard words, and using a word set associated with each standard word as a basic word set;
counting the times of receiving each receiving word in a plurality of receiving words in the receiving message of the specific information queue to determine the receiving times of each receiving word;
determining words existing in both the input message and the received message as common words, determining an importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word, and selecting the common words having the importance coefficients greater than a threshold value as weighted words to determine a plurality of weighted words,
wherein determining the importance coefficient for each common term based on the number of times each common term was received and the number of times each common term was entered comprises:
determining the number of receptions CO of each common termy;
Determining the number of inputs CI for each common termy;
Wherein y is a natural number and is more than or equal to 1 and less than or equal to No, wherein No is the number of public words;
when characters input by a user are received, acquiring a plurality of candidate words corresponding to the characters from a plurality of basic word sets, calculating the matching degree of each candidate word and each weight word in a plurality of weight words, performing weighted calculation on the matching degree of each candidate word and each weight word to determine the priority level of each candidate word, sequencing the candidate words based on the priority level of each candidate word, and providing the candidate words according to the sequencing order;
wherein calculating a degree of matching of each candidate term to each weighted term in the plurality of weighted terms comprises:
performing semantic matching on each candidate word and each weight word in the plurality of weight words, and taking the matching degree of the semantic matching as the matching degree of each candidate word and each weight word in the plurality of weight words;
wherein, performing weighted calculation on the matching degree of each candidate word and each weighted word to determine the priority level of each candidate word comprises:
determining the matching degree M of the ith candidate word and the jth weight wordij;
Determining the weight coefficient Ow of the jth weight wordj;
Based on matching degree M of ith candidate word and jth weight wordijCalculating the priority P of the ith candidate wordi=Mi1×Ow1+Mi2×Ow2+…+Mij×Owj;
Where i and j are natural numbers and 1 ≦ i ≦ N1, 1 ≦ j ≦ N2, N1 is the number of candidate words, and N2 is the number of weighted words.
2. The method of claim 1, wherein an application is an instant messaging application, a financial application, or a gaming application.
3. The method of claim 1, storing the incoming messages and received messages associated with each application in an information queue separately comprises:
input messages associated with each application are stored in an input portion of the information queue and received messages associated with each application are stored in an output portion of the information queue.
4. The method of claim 3, monitoring in real-time a respective first number of incoming messages and second number of received messages in each message queue comprising:
monitoring a first number of all characters included in an input message in an input part of an information queue in real time; and monitoring in real time a second number of all characters comprised by the received message in the output portion of the information queue.
5. The method of claim 1, further comprising setting a respective quantity threshold for each application.
6. A system for information input based on a contextual environment, the system comprising:
the initialization device establishes an information queue for each application in a plurality of applications and respectively stores input messages and received messages associated with each application in the information queue;
the monitoring device monitors the first number of the input messages and the second number of the received messages in each information queue in real time, when the first number of the input messages of the specific information queue is larger than a number threshold value, whether the ratio of the second number to the first number of the specific information queue is within a preset range is determined, and if the ratio is within the preset range, the frequency statistics is carried out on each input word in a plurality of input words in the input messages of the specific information queue so as to determine the input frequency of each input word;
a selection device which selects at least two input words from the plurality of input words as standard words according to the input times, and takes a word set associated with each standard word as a basic word set;
a counting device for counting the times of receiving each of a plurality of receiving words in the receiving message of the specific information queue to determine the receiving times of each receiving word;
determining means for determining words existing in both the input message and the received message as common words, determining an importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word, and selecting the common words having the importance coefficient greater than a threshold value as weighted words to determine a plurality of weighted words, wherein determining the importance coefficient of each common word based on the number of times of reception and the number of times of input of each common word includes:
determining the number of receptions CO of each common termy;
Determining the number of inputs CI for each common termy;
Wherein y is a natural number and is more than or equal to 1 and less than or equal to No, wherein No is the number of public words;
the device comprises a providing device, a judging device and a display device, wherein when characters input by a user are received, a plurality of candidate words corresponding to the characters are obtained from a plurality of basic word sets, the matching degree of each candidate word and each weight word in a plurality of weight words is calculated, the matching degree of each candidate word and each weight word is weighted and calculated to determine the priority level of each candidate word, the candidate words are ranked based on the priority level of each candidate word, and the candidate words are provided according to the ranking order;
wherein calculating a degree of matching of each candidate term to each weighted term in the plurality of weighted terms comprises:
performing semantic matching on each candidate word and each weight word in the plurality of weight words, and taking the matching degree of the semantic matching as the matching degree of each candidate word and each weight word in the plurality of weight words;
wherein, performing weighted calculation on the matching degree of each candidate word and each weighted word to determine the priority level of each candidate word comprises:
determining the matching degree M of the ith candidate word and the jth weight wordij;
Determining the weight coefficient Ow of the jth weight wordj;
Based onMatching degree M of i candidate words and jth weight wordijCalculating the priority P of the ith candidate wordi=Mi1×Ow1+Mi2×Ow2+…+Mij×Owj;
Where i and j are natural numbers and 1 ≦ i ≦ N1, 1 ≦ j ≦ N2, N1 is the number of candidate words, and N2 is the number of weighted words.
7. The system of claim 6, wherein the application is an instant messaging application, a financial application, or a gaming application.
8. The system of claim 6, the initialization means to store the incoming messages and the received messages associated with each application in an information queue separately comprising:
the initialization means stores the input messages associated with each application in an input portion of the information queue and stores the received messages associated with each application in an output portion of the information queue.
9. The system of claim 8, the monitoring device monitoring, in real-time, the respective first number of incoming messages and second number of received messages in each message queue comprising:
the monitoring device monitors a first number of all characters included in an input message in an input part of the information queue in real time; and monitoring in real time a second number of all characters comprised by the received message in the output portion of the information queue.
10. The system of claim 6, further comprising setting a respective quantity threshold for each application.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010646972.3A CN111984132B (en) | 2020-07-07 | 2020-07-07 | Method and system for inputting information according to context environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010646972.3A CN111984132B (en) | 2020-07-07 | 2020-07-07 | Method and system for inputting information according to context environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111984132A CN111984132A (en) | 2020-11-24 |
CN111984132B true CN111984132B (en) | 2021-07-27 |
Family
ID=73438556
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010646972.3A Active CN111984132B (en) | 2020-07-07 | 2020-07-07 | Method and system for inputting information according to context environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111984132B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101681229A (en) * | 2007-04-26 | 2010-03-24 | 株式会社爱可信 | Input candidate providing device, input candidate providing system, input candidate providing method, and input candidate providing program |
CN102419639A (en) * | 2010-09-28 | 2012-04-18 | 英业达股份有限公司 | Input system and method for providing expanded words |
CN102591472A (en) * | 2011-01-13 | 2012-07-18 | 新浪网技术(中国)有限公司 | Method and device for inputting Chinese characters |
CN102937976A (en) * | 2012-10-17 | 2013-02-20 | 北京奇虎科技有限公司 | Drop-down prompting method and apparatus based on input prefix |
CN105051734A (en) * | 2013-04-04 | 2015-11-11 | 索尼公司 | Information processing device, data input assistance method, and program |
CN105094368A (en) * | 2015-07-24 | 2015-11-25 | 上海二三四五网络科技有限公司 | Control method and control device for frequency modulation ordering of input method candidate item |
CN106873799A (en) * | 2017-02-16 | 2017-06-20 | 北京百度网讯科技有限公司 | Input method and device |
CN108319377A (en) * | 2018-02-07 | 2018-07-24 | 北京百度网讯科技有限公司 | Method and system, terminal and the computer readable storage medium of displaying word input |
-
2020
- 2020-07-07 CN CN202010646972.3A patent/CN111984132B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101681229A (en) * | 2007-04-26 | 2010-03-24 | 株式会社爱可信 | Input candidate providing device, input candidate providing system, input candidate providing method, and input candidate providing program |
CN102419639A (en) * | 2010-09-28 | 2012-04-18 | 英业达股份有限公司 | Input system and method for providing expanded words |
CN102591472A (en) * | 2011-01-13 | 2012-07-18 | 新浪网技术(中国)有限公司 | Method and device for inputting Chinese characters |
CN102937976A (en) * | 2012-10-17 | 2013-02-20 | 北京奇虎科技有限公司 | Drop-down prompting method and apparatus based on input prefix |
CN105051734A (en) * | 2013-04-04 | 2015-11-11 | 索尼公司 | Information processing device, data input assistance method, and program |
CN105094368A (en) * | 2015-07-24 | 2015-11-25 | 上海二三四五网络科技有限公司 | Control method and control device for frequency modulation ordering of input method candidate item |
CN106873799A (en) * | 2017-02-16 | 2017-06-20 | 北京百度网讯科技有限公司 | Input method and device |
CN108319377A (en) * | 2018-02-07 | 2018-07-24 | 北京百度网讯科技有限公司 | Method and system, terminal and the computer readable storage medium of displaying word input |
Also Published As
Publication number | Publication date |
---|---|
CN111984132A (en) | 2020-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109815314B (en) | Intent recognition method, recognition device and computer readable storage medium | |
CN112395556B (en) | Abnormal user detection model training method, abnormal user auditing method and device | |
JPH03201167A (en) | Search in data processing system | |
CN103761254A (en) | Method for matching and recommending service themes in various fields | |
CN110795542A (en) | Dialogue method and related device and equipment | |
US8751588B2 (en) | Message thread clustering | |
JP2009098964A (en) | Network service system, server, method and program | |
CN108021622A (en) | Information determination method and device, electronic equipment and storage medium | |
CN106777282B (en) | The sort method and device of relevant search | |
CN111597446B (en) | Content pushing method and device based on artificial intelligence, server and storage medium | |
CN112632257A (en) | Question processing method and device based on semantic matching, terminal and storage medium | |
CN108509499A (en) | A kind of searching method and device, electronic equipment | |
CN116455861B (en) | Big data-based computer network security monitoring system and method | |
CN112287094B (en) | Similar case text retrieval system | |
US20050097067A1 (en) | System and method for combining valuations of multiple evaluators | |
CN104360759B (en) | Candidate word sort method, device and character input method, equipment | |
US20150188866A1 (en) | Message focusing | |
CN111984132B (en) | Method and system for inputting information according to context environment | |
CN106095941B (en) | Big data knowledge base-based solution recommendation method and system | |
CN110609958A (en) | Data pushing method and device, electronic equipment and storage medium | |
CN105045835B (en) | Information search method and device | |
WO2014203402A1 (en) | Information providing device, information providing method, and program | |
CN112148999B (en) | Web API recommendation method based on Mashup service neighborhood under Web open environment | |
CN106557178B (en) | Method and device for updating entries of input method | |
CN108509449A (en) | A kind of method and server of information processing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |