CN101645088B - Determine the method for auxiliary lexicon, device and the input method system that need to load - Google Patents
Determine the method for auxiliary lexicon, device and the input method system that need to load Download PDFInfo
- Publication number
- CN101645088B CN101645088B CN200910137634.0A CN200910137634A CN101645088B CN 101645088 B CN101645088 B CN 101645088B CN 200910137634 A CN200910137634 A CN 200910137634A CN 101645088 B CN101645088 B CN 101645088B
- Authority
- CN
- China
- Prior art keywords
- user
- feature
- auxiliary lexicon
- needing
- load
- 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
Landscapes
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of method that the invention discloses auxiliary lexicon determined and need loading, the method includes: gather the input information of user; Analyze the information that collects, the feature that can characterize user interest preserved in input information and preset features table is compared, and record and feature that feature in mark sheet matches; The auxiliary lexicon needing to load is determined according to the feature recorded. The invention also discloses the device of a kind of auxiliary lexicon determined and need loading and input method system. By the present invention, improve the accuracy judging user interest, for determining that the auxiliary lexicon needing to load provides reliable foundation.
Description
The application is the applying date, and to be on August 5th, 2008, application number be 200810117750.1, name is called the divisional application of application for a patent for invention of " determining the method for auxiliary lexicon, device and input method system that needs load ".
Technical field
The present invention relates to input method field, particularly relate to determine the method for auxiliary lexicon, device and the input method system that need to load.
Background technology
Along with the development of computer technology, input method receives increasingly higher concern as the important means of man-machine interaction. User's requirement to input accuracy and input speed, has promoted input method to develop towards intellectuality, hommization, personalized direction.
Current input method system (including Chinese, Japanese, Korean etc.) is all based on its word bank system provides candidate word for user in input process. For promoting the fluency of user's input, a developing direction of input method software is to expand the entry quantity included, and reduces the number of times word for word selecting word as far as possible, improves the accuracy rate of first-selected word. Therefore, input method system is except basic dictionary, it is also possible to have auxiliary lexicon, namely usually said cell dictionary. Wherein, the entry in basic dictionary is that most of input method user accepts and widely used, has certain versatility. Entry in auxiliary lexicon has specialization, personalized feature, for instance chemical industry dictionary, financing dictionary, American-European film dictionary etc., this dictionary designs for the requirement of intellectualization of input method for the user in different majors field, different interest. Fully, reasonably utilize these dictionaries to can aid in raising user and input accuracy and input speed.
But dictionary scale can not be pursued large and complete simply, repeated code conflict, hydraulic performance decline, software size otherwise can be brought to become the adverse effect such as big. Simultaneously the professional field of user and interest are also diversified, unified to a large and complete dictionary and unrealistic. A kind of processing scheme is according to each user concrete needs at specific area, loads relevant auxiliary lexicon, wherein, how to judge that user needs to load which auxiliary lexicon and becomes the problem that comparison is crucial.
The method loading auxiliary lexicon at present is to be currently entered the relevant information of environment according to user, loads corresponding auxiliary lexicon, because being currently entered environment may characterize professional field or the interest of user. The wherein said environment that is currently entered includes current application program title, current window title, file name etc. Such as, the current input environment of user is certain online game interface, then automatically load the auxiliary lexicon of this game; When user uses input method in certain document, then automatically load the auxiliary lexicon matched with the content in the document title or document.
But, owing to the title of document is usually arbitrarily edited by user, it is called for short " document ", " work ", " memorandum " etc., the title general such as some document " new files 1 ", " new files 2 " that then directly use is given tacit consent to, therefore judges and loads relevant auxiliary lexicon have limitation from filename, program name. It addition, carry out judging also not accurately according to the content in document, because the document is not necessarily what active user edited, its content differs and characterizes the interest of active user surely. And it would furthermore be possible to the judgement made the mistake, document such as, occurs in that " chemical industry " word, is then loaded with chemical industry dictionary, but actually document occurs that " procedure work ", obvious the document might not be relevant to chemical industry, and such loading can harm users be experienced on the contrary.
Therefore, present stage needs one that those skilled in the art urgently solve technical problem is that, how accurately to judge user's art or user interest, provides reliable foundation for loading the auxiliary lexicon needed.
Summary of the invention
In view of this, it is an object of the invention to provide and determine the method for auxiliary lexicon, device and the input method system needing to load, with solve prior art to determine to need to load user thesaurus time inaccurate problem.
For achieving the above object, the invention provides following scheme:
A kind of method determining the auxiliary lexicon needing loading, including:
Gather the input information of user; Wherein, the input information of described user includes the list entries of user;
Analyze the list entries of described user collected, the feature that can characterize user interest preserved in list entries and preset features table is compared, and record and feature that feature in mark sheet matches;
The auxiliary lexicon needing to load is determined according to the feature recorded.
Preferably, also include: when input method system is called, described mark sheet is loaded in internal memory.
Preferably, when meeting trigger condition, determine the auxiliary lexicon needing to load according to the feature recorded.
Preferably, the feature of record is added up, determine the auxiliary lexicon needing to load according to statistical result.
Preferably, based on preset statistical model, the feature recorded is added up; Described statistical model is the weight vectors of several features.
Preferred: based on preset statistical model, according to the feature recorded, each auxiliary lexicon to be marked, appraisal result is defined as higher than the auxiliary lexicon of preset threshold value the auxiliary lexicon needing to load.
Preferred: based on preset statistical model, according to the feature recorded, all auxiliary lexicons to be carried out Comprehensive Assessment, calculate the probability that each auxiliary lexicon needs to load, probability sorting auxiliary lexicon before preset threshold value is defined as the auxiliary lexicon needing to load.
Preferably, based on preset rule model, the feature recorded is added up; Described rule model is think the rule arranged.
Preferably, the input information of described user also includes:
Content in user thesaurus, the environmental information of user's input and input behavior;
Described method also includes:
Analyze the content in the described dictionary that collects, the environmental information of user's input and input behavior, compare with the feature that can characterize user interest preserved in preset features table, and record and feature that feature in mark sheet matches;
The auxiliary lexicon needing to load is determined according to the feature recorded.
Preferably, also include:
Recommend or automatically load the described auxiliary lexicon needing and loading.
Preferably, also include:
The relevant information loading auxiliary lexicon is saved in server; Described relevant information comprises the auxiliary lexicon list of loading and/or entry list and/or auxiliary lexicon service condition.
A kind of device determining the auxiliary lexicon needing loading, including:
Information acquisition unit, for gathering the input information of user; Wherein, the input information of described user includes the list entries of user;
Analytic unit, for analyzing the list entries of the described user collected, compares the feature that can characterize user interest preserved in list entries and preset features table, and records and feature that feature in mark sheet matches;
Judging unit, for determining the auxiliary lexicon needing to load according to the feature recorded.
Preferably, described judging unit includes:
Triggers unit, is used for judging whether to meet trigger condition;
First performs subelement, for determining the auxiliary lexicon needing to load according to the feature recorded.
Preferably, described judging unit includes:
Statistics subelement, for adding up the feature recorded;
Second performs subelement, for determining the auxiliary lexicon needing to load according to statistical result.
Preferred:
The feature recorded is added up by described statistics subelement based on preset statistical model; Described statistical model is the weight vectors of several features.
Preferably, described statistics subelement includes:
Scoring subelement, for based on preset statistical model, marking to each auxiliary lexicon according to the feature recorded;
Relatively subelement, for the auxiliary lexicon being defined as higher than the auxiliary lexicon of preset threshold value needing to load by scoring.
Preferably, described statistics subelement includes:
Probability calculation subelement, for based on preset statistical model, all auxiliary lexicons being carried out Comprehensive Assessment according to the feature recorded, calculates the probability that each auxiliary lexicon is likely to need to load;
Select subelement, for the auxiliary lexicon being defined as needing to load by probability sorting auxiliary lexicon before preset threshold value.
Preferred:
The feature recorded is added up by described statistics subelement based on preset rule model; Described rule model is the artificial rule arranged.
Preferred: content, the environmental information of user's input and the input behavior that described information acquisition unit is additionally operable to gather in user thesaurus;
Content, the environmental information of user's input and the input behavior that described analytic unit is additionally operable to analyze in the described dictionary collected, compare with the feature that can characterize user interest preserved in preset features table, and record and the feature that matches of feature in mark sheet;
Described judging unit is additionally operable to determine, according to the feature recorded, the auxiliary lexicon needing to load.
Preferably, also include:
Event responds unit, for recommending or automatically loading the described auxiliary lexicon needing and loading.
Preferably, also include:
Account management unit, for user bound, and is saved in server by the relevant information loading auxiliary lexicon; Described relevant information comprises the auxiliary lexicon list of loading and/or entry list and/or auxiliary lexicon service condition.
A kind of input method system, including:
Information acquisition unit, for gathering the input information of user, described input information includes the content in the list entries of user, user thesaurus, the environmental information of user's input and input behavior;
Analytic unit, for analyzing the list entries of the described user collected, compares the feature that can characterize user interest preserved in list entries and preset features table, and records and feature that feature in mark sheet matches;
Judging unit, for determining the auxiliary lexicon needing to load according to the feature recorded;
Event responds unit, for recommending or automatically loading the described auxiliary lexicon needing and loading.
Preferably, described judging unit includes:
Triggers unit, is used for judging whether to meet trigger condition;
First performs subelement, for determining the auxiliary lexicon needing to load according to the feature recorded.
Preferably, described judging unit includes:
Statistics subelement, for adding up the feature recorded;
Second performs subelement, for determining the auxiliary lexicon needing to load according to statistical result.
Preferred: the feature recorded is added up by described statistics subelement based on preset statistical model; Described statistical model is the weight vectors of several features.
Preferred: the feature recorded is added up by described statistics subelement based on preset rule model; Described rule model is the artificial rule arranged.
Preferably, also include:
Account management unit, for user bound, and is saved in server by the relevant information loading auxiliary lexicon; Described relevant information comprises the auxiliary lexicon list of loading and/or entry list and/or auxiliary lexicon service condition.
According to specific embodiment provided by the invention, the invention discloses techniques below effect:
First, the input information of user is analyzed by the present invention, the feature that can characterize user interest preserved in input information and preset features table is compared, and records the feature matched with the feature in mark sheet, in this, as the Main Basis determining the auxiliary lexicon needing loading; Owing to the input information of user can extract the feature characterizing user interest more accurately, therefore for determining that the auxiliary lexicon needing to load provides reliable foundation.
Second, it is possible to by the data accumulation in one period, the feature of record is added up, it is possible to improve the accuracy judged further.
3rd, when gathering user's input information, not only gather the list entries of user, can be combined with the integrated informations such as the entry in the current input environment of user, user's input behavior, user thesaurus (the long-term input of user) to be analyzed, contribute to filtering out interference information, make the user interest judged more accurate.
4th, the relevant information (the auxiliary lexicon list of loading, entry list, auxiliary lexicon service condition etc.) loading auxiliary lexicon can be preserved on the server by account management, user obtains, after completing Account Logon, the relevant information loading auxiliary lexicon from server so that user also is able to use the relevant information loading auxiliary lexicon on other computers. Further, since there is many people to use the situation of same computer, the administrative mechanism that accesses to your account can also avoid the interference between different users.
5th, after the professional field knowing user or interest, the present invention can when first time Setup Wizard, update guide time or user carry out the loading of corresponding auxiliary lexicon when inputting in real time, the mode loaded can also be recommend prompting or automatically load, hence in so that the mode loaded is more flexible and hommization; Wherein recommend the interaction embodying between user in the mode loaded, contribute to getting the information of exact representation user interest more, reduce the probability that harm users is experienced.
Accompanying drawing explanation
Fig. 1 is the flow chart of the method that the embodiment of the present invention provides;
Fig. 2 is the schematic diagram of the first device that the embodiment of the present invention provides;
Fig. 3 is the schematic diagram of the second device that the embodiment of the present invention provides;
Fig. 4 is the schematic diagram of the 3rd device that the embodiment of the present invention provides;
Fig. 5 is the schematic diagram of the 4th device that the embodiment of the present invention provides;
Fig. 6 is the schematic diagram of the 5th device that the embodiment of the present invention provides;
Fig. 7 is the schematic diagram of the 6th device that the embodiment of the present invention provides;
Fig. 8 is the schematic diagram of the first input method system that the embodiment of the present invention provides;
Fig. 9 is the schematic diagram of the second input method system that the embodiment of the present invention provides;
Figure 10 is the schematic diagram of the 3rd input method system that the embodiment of the present invention provides;
Figure 11 is the schematic diagram of the 4th input method system that the embodiment of the present invention provides;
Figure 12 is the schematic diagram of the 5th input method system that the embodiment of the present invention provides.
Detailed description of the invention
A kind of method that the invention provides auxiliary lexicon determined and need loading, understandable for making the above-mentioned purpose of the present invention, feature and advantage become apparent from, below in conjunction with the drawings and specific embodiments, the present invention is described in more detail.
Referring to Fig. 1, the method determining the auxiliary lexicon needing loading provided by the invention comprises the following steps:
S101: gather the input information of user;
In the embodiment of the present invention, described input information can be the information such as the input behavior of list entries, the input environment of user or user. In the embodiment of the present invention, input mode can include keyboard symbol, hand-written information and phonetic entry etc., and therefore described list entries can include coded string, hand-written information, speech input information etc.
S102: analyze the information collected, record the feature that can characterize user interest in described information;
The information that user is inputted by the present invention, as the foundation passing judgment on user interest, therefore directly extracts the feature that can characterize user interest from the input information of user. Such as, in the list entries of user, described feature can include the entry of the Feature Words such as " chemical industry ", " Warcraft ", frequency etc., owing to Feature Words itself is likely to be of certain discrimination, such as, entry " is sought group " and is frequently appeared in online game, but this word does not have the discrimination judging which kind of online game concrete. Therefore, described feature is possible not only to include the frequency of Feature Words, entry number and the tightness degree of Feature Words in list entries, it is also possible to the information such as discrimination including Feature Words.
S103: determine the auxiliary lexicon needing to load according to the feature recorded.
Visible, the input information of user is analyzed by the embodiment of the present invention, and therefrom extract the feature that can characterize user interest, owing to these features can characterize the interest of user to a greater extent, therefore external with dependence input environment carries out compared with interest judgement, it is possible to extract the information representing user interest more exactly. For determining that the auxiliary lexicon needing to load provides relatively reliable foundation.
In actual applications, for the feature in convenient record user's input information, the mode of preset features table can be adopted, the feature that can characterize user interest is saved in this mark sheet, and it is loaded in internal memory when user calls input method, when so analyzing user's input information, directly input information can be compared with the feature in mark sheet, such as, if input information occurs the feature matched with the feature in mark sheet, then record the features such as the entry of this feature matched, word frequency, discrimination.
In order to the method making the present invention is more efficient, it is possible to the information through one period carries out data accumulation, then the data according to accumulation go to judge the interest of user. It is therefore possible to use set the mode of trigger condition, when a triggering condition is met, the auxiliary lexicon needing to load is determined according to the feature of record. Wherein, described trigger condition can be whether reach predetermined length integration time, whether the data of accumulation reach predetermined quantity or whether user terminates to call input method etc. Alternatively, it is also possible to the feature of bulk registration is added up, determine the auxiliary lexicon needing to load according to the result of statistics.
Wherein, the mode that the feature recorded is added up can have multiple, and several preferred mode is described below, and is used only for illustrating the realization of the present invention, and should not be construed as limitation of the present invention.
Mode one: based on preset statistical model, the feature of record is added up. Described preset statistical model can be trained by developer in the development phase, this statistical model can be that (some each users input sample according to the language material marked, general each sample is by manually determining whether this loading dictionary, it is possible to regard a multiple target classification problem in machine learning as) training pattern. Owing to each feature is different to the reference value judging user interest, therefore can by the different different weights of feature imparting be realized. Such as, there is discrimination and frequency in each entry: the discrimination in " Alterac mountain valley ", " rough pawl cave " is significantly high, and their appearance almost can be inferred that the interest of Warcraft aspect, but the frequency that they occur is relatively low; " magic ", " injury " then contrast, because the two entry also usually occurs in other linguistic context. It is usually and to consider the two factor, to each entry with than suitable weight. Therefore, the statistical model trained can show as the weight vectors of some features, in such as certain classification auxiliary lexicon, the weight vectors of each feature is<0.33,-0.11,0.1 ... 0.03,0.001>, it is possible to the weight of expression feature 1 is 0.33, the value that the weight of feature 2 is negative for-0.11(represents that the appearance of this feature is unfavorable to recommending this dictionary, is negative characteristics). When recording the feature in input content, it is possible to being expressed as the form of vector, each characteristic parameter can be recorded as simply and appear as 1, occur without is 0, it is also possible to represented by series of discrete value. Thus will determine that user interest this qualitatively problem be converted into quantitative problem, make the result that statistics obtains have higher reliability, then determine according to this result be likely to need load auxiliary lexicon.
According to preset model to record feature add up, with determine be likely to need load auxiliary lexicon time, various ways can also be adopted, such as can based on preset statistical model, according to the feature recorded, each auxiliary lexicon is marked, scoring is defined as higher than the auxiliary lexicon of certain preset threshold value the auxiliary lexicon being likely to need to load. Result of wherein giving a mark can be carried out dot product by the characteristic vector recorded with the feature weight vector in model and obtain. Such as in once statistics, record obtains about the characteristic vector of certain classification auxiliary lexicon being<1,0,1.33, ..., 0.78,0.46>, the feature weight vector in statistical model is<0.33 ,-0.11,0.1 ... 0.03,0.001>, then this statistics for the marking result of category auxiliary lexicon is: 1 �� 0.33+0 �� (-0.11)+...+0.46 �� 0.001, then judge that whether this marking result is more than certain preset threshold value, if it is greater, then the auxiliary lexicon of the category to be defined as the auxiliary lexicon needing to load. In addition, it is also based on preset model, the probability loaded is needed according to each auxiliary lexicon of the feature calculation recorded, probability is defined as higher than the auxiliary lexicon of preset threshold value the auxiliary lexicon being likely to need to load, or by each probit by being ranked up from high to low, the auxiliary lexicon of ranking former is defined as the auxiliary lexicon needing to load.
Mode two: the feature recorded is added up based on preset rule model. This rule model can be the rule that developer passes through that the various means such as experience arrange, very simple form can be established as, such as: if there being the mark sheet of 7 and above hit Warcraft dictionary in 50 words inputting continuously of user, then Warcraft dictionary is defined as the auxiliary lexicon being likely to need to load.
Wherein, what the input information of the described user that the embodiment of the present invention gathers may refer to user directly inputs sequence; Simultaneously, due to the content inputted before the environmental information of user's input, the input behavior of user and user, interest for passing judgment on user all has certain help, if considering these information, then can judge the interest of user more exactly, for determining that the auxiliary lexicon needing to load provides stronger foundation. Therefore, in a preferred embodiment of the invention, the input information gathered can not only include the direct list entries of user, the entry (entry that user inputted in the past) in the environmental information (include host program, installation procedure list, fire wall are arranged) of input, the input behavior (include whether word for word upper screen, whether use backspace key, average page turning to select word number of times etc.) of user and user thesaurus can also be included, equally these information are analyzed, the feature that record wherein occurs. Such as, analyze time, it is possible to using user directly input sequence as pass judgment on Main Basis, input behavior information according to user simultaneously, the wrong entry that will accidentally input, user no longer include feature candidate word in after deleting, has therefore possessed the function filtering noise data. Finally all features of record are added up, it is possible to obtain the information characterizing user interest more exactly, it is determined which auxiliary lexicon is probably the auxiliary lexicon needing to load.
After utilizing said method to judge the auxiliary lexicon being likely to need to load, it is possible to complete to load the step of auxiliary lexicon. When loading auxiliary lexicon, the present invention can adopt the mode of loading automatically, namely after judging the auxiliary lexicon being likely to need to load, if the credibility of this judgement is higher, then can be loaded directly into these auxiliary lexicons; But when the credibility judged is not as high, automatically load and be likely to hurt on the contrary the experience of user, cause the dislike of user, therefore the present invention can also adopt the mode recommending to load, namely after judging the auxiliary lexicon being likely to need to load, first making recommendation to user, prompting user can load these auxiliary lexicons, then loads after user determines or after making a choice again.
The benefit recommending to load is adopted to also reside in, it is possible to achieve and the interaction between user, the feedback receiving user can judge the true interest of user better. The mode simultaneously automatically loaded would be likely to occur such a hidden danger: user opens multiple application program simultaneously, and is likely to switch between program. Now may judging multiple auxiliary lexicon needing and loading, if all automatically loading these auxiliary lexicons, being then likely to so that committed memory is too much, influential system performance. Hence with the mode recommended, which dictionary user selects to need to load according to actual needs, and judges to need to load but the nonoptional auxiliary lexicon of user will not be loaded, thus avoiding the problems referred to above.
But, no matter it is automatically load or recommend to load, all it is likely to face such a problem: if user program is in screen mode toggle (such as online games such as Warcrafts) at that time, judge can automatically load auxiliary lexicon to user or make recommendation, then send to the webserver and download this dictionary or eject the request recommending prompting. If this request is intercepted by network firewall causes that prompting frame ejects, it will bringing the user carrying out playing and greatly dislike, harm users is experienced. Therefore, the embodiment of the present invention can also formulate recommendation rules, such as regulation " user runs program under screen mode toggle and then not recommends or automatically load ". In actual applications, this recommendation rules can combine with statistical model when judging or rule model, for instance: statistics scoring is more than after certain threshold value, in addition it is also necessary to meeting this recommendation rules could recommend or automatically load. It is of course also possible to so do not formulate recommendation rules, and using whether this feature full frame is as a negative effect of statistical model, its weight is set to the negative value that absolute value is higher, it is also possible to reach same purpose.
The above all carries out when user inputs in real time recommending or automatically loading auxiliary lexicon, in order to make application more flexible, the present invention can also utilize Setup Wizard to carry out loading or recommending when installing input method in first time, now the main auxiliary lexicon judging according to information such as environmental informations, installation procedure to be likely to need to load; Can also carry out loading or recommending when update guide, now the main auxiliary lexicon judging according to the content information in user thesaurus and environmental information to be likely to need to load.
It addition, the present invention can realize the recommendation process of iteration, when the user interest that accumulation data judgement makes new advances, and then when judging the auxiliary lexicon being likely to needs loading made new advances, then give the recommendation made new advances; Meanwhile, when judging that the service condition of certain auxiliary lexicon is had in limited time by user, it is possible to prompting user unloads this dictionary.
In the process described above, the relevant information (including the information such as the auxiliary lexicon list of loading, entry list, auxiliary lexicon service condition) having loaded auxiliary lexicon generally can be saved in computer this locality. But in actual applications, it is also possible to there are such two kinds of situations: a kind of is then have more people to use same computer in the public places such as different members in family uses same computer, Internet bar. Generally all there is due to different people different professional fields or interest, be saved in the relevant information loading auxiliary lexicon on same computer, it is possible to the interference between different users can be caused. Another kind of situation is, same user is likely to use different computers, such as office computer, home computer, other portable computers etc., if the relevant information loading auxiliary lexicon is saved in this locality, then this user will be unable to use these information on other computers. Therefore, in a preferred embodiment of the invention, it is possible to adopt account management mechanism, distinguish different users according to account name, and utilize account management server to carry out synchronizing information so that the relevant information having loaded auxiliary lexicon can preserve on the server. After such user logs in, then can make corresponding recommendation according to different users, simultaneously, user can obtain renewal from server, the relevant information loading auxiliary lexicon is updated on currently used any computer, even if making user change computer, it is also possible on the computer after replacing, direct use has loaded the relevant information of auxiliary lexicon.
Understandable in order to make present invention described above embodiment become apparent from, further introduce below by the example in two concrete application scenarios.
Use scene one: input method user A recommends when input method is upgraded to the new edition supporting auxiliary lexicon to recommend. Installation procedure analyzes local user thesaurus, judge that the input entry in the user thesaurus of user A relates to chemical industry, financing, the American-European several specialty/category of interest of film and credibility higher, and Jiangxi, outdoor activity, automobile, four classifications of house property credibility more relatively low. A certain step at Setup Wizard, the dialog box that program dynamically generates, prompt the user whether to need to load these auxiliary lexicons: acquiescence has chosen chemical industry, financing, American-European film dictionary, point out but do not choose Jiangxi, outdoor activity, automobile, four dictionaries of house property, it is provided that " more dictionary " is for dictionary function of search. User A has chosen " Jiangxi " and " outdoor activity " auxiliary lexicon on this basis. After auxiliary lexicon loads, the input data of user are still used in follow-up analysis, when finding that user interest changes, it is possible to can recommend new auxiliary lexicon, the existing dictionary of prompting unloading.
Use scene two: user B plays online game World of Warcraft Internet bar, after entering screen mode toggle this user recall input method discuss with a player together with go battlefield, Alterac mountain valley task to practice level. The characteristic information that input method software obtains includes: host program World of Warcraft; User input content comprises the Feature Words that the discrimination such as " Alterac mountain valley ", " rough pawl cave ", " frost wolf ", " glug Longde ", " thunder lance medal " is higher; Comprise the supplemental characteristic word that the discrimination such as " forming a team ", " alliance ", " coordinate ", " battlefield ", " magic bottle " is relatively low; User takes word for word screen connection mode when inputting these Feature Words. Input method judges that this user has loading Warcraft auxiliary lexicon demand by analysis, and points out active user when this machine firewall rule detected is network interaction. In this case input method selects to prompt the user whether to load after network game is exited. User selects " loading ", allows firewall rule to be revised as dictionary simultaneously and loads network of relation operation for " automatically ". Input method software loads Warcraft auxiliary lexicon after user B is again introduced into World of Warcraft, and this dictionary has during renewal automatically to download. This scene is under cafe environment, and user does not carry out input method Account Logon, and what user interest judgement was taked is the real-time mode for user input sequence.
Corresponding with the method that the embodiment of the present invention provides, the embodiment of the present invention additionally provides the device of a kind of auxiliary lexicon determined and need loading, and referring to Fig. 2, this device includes:
Information acquisition unit U201, for gathering the input information of user;
Analytic unit U202, for analyzing the information collected, records the feature that can characterize user interest in described information;
Judging unit U203, for determining the auxiliary lexicon needing to load according to the feature recorded.
User calls input method when inputting, and information acquisition unit U201 gathers the input information of user; The information collected is analyzed by analytic unit U202, the feature that can characterize user interest occurred in the information collected described in record, and then judging unit U203 determines the auxiliary lexicon needing to load according to the feature recorded.
Analytic unit U202 can adopt various ways to complete the analysis to the information collected, it is preferred that, it is judged that described in whether the information that collects exists the feature matched with the feature in preset features list, if it is present the feature matched described in record. Referring to Fig. 3, analytic unit U302 may further include:
Judgment sub-unit U3021, is used in the information collected described in judging and whether there is the feature matched with the feature in preset features list;
Record subelement U3022, is used for the feature matched described in recording.
Information acquisition unit U301 in Fig. 3 and judging unit U303 is identical with the information acquisition unit U201 in Fig. 2 and judging unit U203.
In order to be more conducive to judge the interest of user, it is possible to determining the auxiliary lexicon needing to load after data accumulation after a while again, therefore, referring to Fig. 4, it is judged that unit U403 can include following two subelement:
Triggers unit U4031, is used for judging whether to meet trigger condition;
First performs subelement U4032, for determining the auxiliary lexicon needing to load according to the feature recorded.
Information acquisition unit U401 in Fig. 4, analytic unit U402 are identical with the information acquisition unit U201 in Fig. 2, analytic unit U202.
It addition, referring to Fig. 5, it is judged that unit U503 can also include following two subelement:
Statistics subelement U5031, for adding up the feature recorded;
Second performs subelement U5032, for determining the auxiliary lexicon needing to load according to statistical result.
Wherein, statistics subelement U5031 can also adopt various ways that the feature recorded is added up, and a kind of preferably based on preset statistical model, the feature recorded is added up. In this manner, statistics subelement U5031 may include that
Scoring subelement U50311, for based on preset model, marking to each auxiliary lexicon according to the feature recorded;
Relatively subelement U50312, for the auxiliary lexicon being defined as higher than the auxiliary lexicon of preset threshold value needing to load by scoring.
Information acquisition unit U501 in Fig. 5, analytic unit U502 are identical with the information acquisition unit U201 in Fig. 2, analytic unit U202.
Referring to Fig. 6, statistics subelement U6031 can also farther include:
Probability calculation subelement U60311, for based on preset model, all auxiliary lexicons being carried out Comprehensive Assessment according to the feature recorded, calculates the probability that each auxiliary lexicon is likely to need to load;
Select subelement U60312, for the auxiliary lexicon being defined as needing to load by probability sorting auxiliary lexicon before preset threshold value.
Information acquisition unit U601 in Fig. 6, analytic unit U602, judging unit U603, second perform subelement U6032, with the information acquisition unit U501 in Fig. 5, analytic unit U502, judging unit U503, second to perform subelement U5032 identical.
Another kind preferably, added up by statistics subelement U6031 based on preset rule by the feature recorded.
In order to be accurately obtained the information characterizing user interest, filter out interference information, in a preferred embodiment of the invention, information acquisition unit U201 gather user's input information can include the content in the list entries of user, user thesaurus, user input environmental information and input behavior, all these information are analyzed by analytic unit U202, and record the feature that wherein can characterize user interest.
After judging the auxiliary lexicon needing to load, it is possible to recommending to load the described auxiliary lexicon needing and loading to user, or automatically load, referring to Fig. 7, this device also includes event responds unit U704, for recommending or automatically loading the described auxiliary lexicon needing and loading.
Interference problem between the user produced when using a computer in order to avoid multiple users, and same user uses and cannot directly use, during multiple stage computer, the problem loading auxiliary lexicon relevant information, this device can also include account management unit U705, for user bound, and the relevant information loading auxiliary lexicon is saved in server. User can sign in server by account administrative unit U705, just may identify which out the identity of user, makes corresponding recommendation respectively according to different users, and the relevant information loading auxiliary lexicon is saved on server. Even if user calls input method on other computers, it is also possible to obtain, from server, the information loading auxiliary lexicon by account administrative unit U705.
Information acquisition unit U701 in Fig. 7, analytic unit U702, judging unit U703 are identical with the information acquisition unit U201 in Fig. 2, analytic unit U202, judging unit U203 respectively.
Referring to Fig. 8, the figure shows a kind of input method system, this system includes:
Information acquisition unit U801, for gathering the input information of user, described input information includes the content directly inputted in sequence, user thesaurus of user, the environmental information of user's input and input behavior;
Analytic unit U802, for analyzing the information collected, records the feature that can characterize user interest in described information;
Judging unit U803, for determining the auxiliary lexicon needing to load according to the feature recorded;
Event responds unit U804, for recommending or automatically loading the described auxiliary lexicon needing and loading.
In actual applications, it is possible in original input method system, increase above-mentioned each unit, realize determining the auxiliary lexicon needing to load, and recommend or automatically load the function of the described auxiliary lexicon needing and loading. For convenience, this system is described in detail by the instantiation in applying below by.
Referring to Fig. 9, this input method system may include that
Input content receives unit U901, for receive sequence that terminal use inputted by various input tools (qwerty keyboard, 9 key boards, handwriting pad etc.) (phonetic, five, natural code, handwriting recognition results, voice sequence or other input forms), map it onto unified coded sequence.
Decoding unit U902, resolves for input content is received coded sequence incoming for unit U901, transfers to candidate generation unit U903 to generate candidate.
Candidate generation unit U903, for the decoding sequence obtained is processed, generates candidate list, event responds unit U908 transfers to user to select. The process that candidate generates, can be first search rm-cell U904 provide input method dictionary (basic dictionary/auxiliary lexicon) and user thesaurus check whether exist mate list entries entry, otherwise carry out group word, give the dictionary of separate sources with different weights, use dynamic programming to find optimal path. The loading of the relevant auxiliary lexicon of user interest, is an important supplement of input method dictionary, can promote the fluency of user's input to a certain extent.
Rm-cell U904, provides various dictionary resource for generating candidate for candidate generation unit U903, including the basic dictionary of input method, group word information storehouse, local user vocabulary, user configuration information, and the auxiliary lexicon being selected by user or automatically loading.
Information acquisition unit U905, for gathering the input information of user, described input information includes long term data (content in user thesaurus) and the short-term data (content that user is currently entered) of user's input, the environmental information also including being currently entered, the input behavior information of user.
Analytic unit U906, for analyzing the information collected, records the feature that can characterize user interest in described information.
Judging unit U907, for determining the auxiliary lexicon needing to load according to the feature recorded.
Event responds unit U908, for recommending or automatically loading the described auxiliary lexicon needing and loading.
Wherein, input content receives unit U901, decoding unit U902, candidate generation unit U903, rm-cell U904 can be the basic functional units of input method system. Input method system of the present invention can be list entries and the relevant context information etc. that original input method system collects user, and judge whether to the auxiliary lexicon of loading with this, then pass through the mode recommended or automatically load and load the described auxiliary lexicon needing and loading, to reach the purpose facilitating user to input.
Referring to Figure 10, it is judged that unit U1007 can include following two subelement:
Triggers unit U10071, is used for judging whether to meet trigger condition;
First performs subelement U10072, for determining the auxiliary lexicon needing to load according to the feature recorded.
Input content in Figure 10 receives unit U1001, decoding unit U1002, candidate generation unit U1003, rm-cell U1004, information acquisition unit U1005, analytic unit U1006, event responds unit U1008, receives unit U901, decoding unit U902, candidate generation unit U903, rm-cell U904, information acquisition unit U905, analytic unit U906, event responds unit U908 respectively with the input content in Fig. 9 identical.
Referring to Figure 11, it is judged that unit 1107 can also include following two subelement:
Statistics subelement U11071, for adding up the feature recorded;
Second performs subelement U11072, for determining the auxiliary lexicon needing to load according to statistical result.
Wherein, statistics subelement U11071 can adopt and based on preset statistical model, the feature recorded added up, or carries out the statisticals such as statistics based on the preset rule feature to recording.
Input content in Figure 11 receives unit U1101, decoding unit U1102, candidate generation unit U1103, rm-cell U1104, information acquisition unit U1105, analytic unit U1106, event responds unit U1108, receives unit U901, decoding unit U902, candidate generation unit U903, rm-cell U904, information acquisition unit U905, analytic unit U906, event responds unit U908 respectively with the input content in Fig. 9 identical.
In order to avoid multiple users use the interference problem of a computer generation, and same user uses the problem that cannot directly use auxiliary lexicon relevant information produced during multiple stage computer, referring to Figure 12, this input method system can also include account management unit U1209, for user bound, and the relevant information loading auxiliary lexicon is saved in server, wherein, the described relevant information having loaded auxiliary lexicon can include the auxiliary lexicon list of loading, entry list, auxiliary lexicon service condition etc. User is after logging in by account administrative unit U1209, it is possible to mutual with remote server, to obtain user thesaurus, user configuration information and to have loaded the renewal of the content such as relevant information of auxiliary lexicon.
Input content in Figure 12 receives unit U1201, decoding unit U1202, candidate generation unit U1203, rm-cell U1204, information acquisition unit U1205, analytic unit U1206, judging unit U1207, event responds unit U1208, receives unit U901, decoding unit U902, candidate generation unit U903, rm-cell U904, information acquisition unit U905, analytic unit U906, judging unit U907, event responds unit U908 respectively with the input content in Fig. 9 identical.
Above to the method for auxiliary lexicon, device and the input method system determined and need to load provided by the present invention, it is described in detail, principles of the invention and embodiment are set forth by specific case used herein, and the explanation of above example is only intended to help to understand method and the core concept thereof of the present invention; Simultaneously for one of ordinary skill in the art, according to the thought of the present invention, all will change in specific embodiments and applications. In sum, this specification content should not be construed as limitation of the present invention.
Claims (27)
1. the method determining the auxiliary lexicon needing loading, it is characterised in that including:
Gather the input information of user; Wherein, the input information of described user includes the list entries of user;
Analyze the list entries of described user collected, the feature that can characterize user interest preserved in list entries and preset features table is compared, and record and feature that feature in mark sheet matches;
The auxiliary lexicon needing to load is determined according to the feature recorded.
2. method according to claim 1, it is characterised in that also include: when input method system is called, described mark sheet is loaded in internal memory.
3. method according to claim 1, it is characterised in that when meeting trigger condition, determines the auxiliary lexicon needing to load according to the feature recorded.
4. method according to claim 1, it is characterised in that the feature recorded is added up, determines the auxiliary lexicon needing to load according to statistical result.
5. method according to claim 4, it is characterised in that the feature recorded is added up based on preset statistical model; Described statistical model is the weight vectors of several features.
6. method according to claim 5, it is characterised in that:
Based on preset statistical model, according to the feature recorded, each auxiliary lexicon is marked, appraisal result is defined as higher than the auxiliary lexicon of preset threshold value the auxiliary lexicon needing to load.
7. method according to claim 5, it is characterised in that:
Based on preset statistical model, according to the feature recorded, all auxiliary lexicons are carried out Comprehensive Assessment, calculate the probability that each auxiliary lexicon needs to load, probability sorting auxiliary lexicon before preset threshold value is defined as the auxiliary lexicon needing to load.
8. method according to claim 4, it is characterised in that the feature recorded is added up based on preset rule model; Described rule model is the artificial rule arranged.
9. method according to claim 1, it is characterised in that the input information of described user also includes:
Content in user thesaurus, the environmental information of user's input and input behavior;
Described method also includes:
Analyze the content in the described dictionary that collects, the environmental information of user's input and input behavior, compare with the feature that can characterize user interest preserved in preset features table, and record and feature that feature in mark sheet matches;
The auxiliary lexicon needing to load is determined according to the feature recorded.
10. method according to claim 1, it is characterised in that also include:
Recommend or automatically load the described auxiliary lexicon needing and loading.
11. method according to claim 10, it is characterised in that also include:
The relevant information loading auxiliary lexicon is saved in server; Described relevant information comprises the auxiliary lexicon list of loading and/or entry list and/or auxiliary lexicon service condition.
12. the device determining the auxiliary lexicon needing loading, it is characterised in that including:
Information acquisition unit, for gathering the input information of user; Wherein, the input information of described user includes the list entries of user;
Analytic unit, for analyzing the list entries of the described user collected, compares the feature that can characterize user interest preserved in list entries and preset features table, and records and feature that feature in mark sheet matches;
Judging unit, for determining the auxiliary lexicon needing to load according to the feature recorded.
13. device according to claim 12, it is characterised in that described judging unit includes:
Triggers unit, is used for judging whether to meet trigger condition;
First performs subelement, for determining the auxiliary lexicon needing to load according to the feature recorded.
14. device according to claim 12, it is characterised in that described judging unit includes:
Statistics subelement, for adding up the feature recorded;
Second performs subelement, for determining the auxiliary lexicon needing to load according to statistical result.
15. device according to claim 14, it is characterised in that:
The feature recorded is added up by described statistics subelement based on preset statistical model; Described statistical model is the weight vectors of several features.
16. device according to claim 15, it is characterised in that described statistics subelement includes:
Scoring subelement, for based on preset statistical model, marking to each auxiliary lexicon according to the feature recorded;
Relatively subelement, for the auxiliary lexicon being defined as higher than the auxiliary lexicon of preset threshold value needing to load by scoring.
17. device according to claim 15, it is characterised in that described statistics subelement includes:
Probability calculation subelement, for based on preset statistical model, all auxiliary lexicons being carried out Comprehensive Assessment according to the feature recorded, calculates the probability that each auxiliary lexicon is likely to need to load;
Select subelement, for the auxiliary lexicon being defined as needing to load by probability sorting auxiliary lexicon before preset threshold value.
18. device according to claim 14, it is characterised in that:
The feature recorded is added up by described statistics subelement based on preset rule model; Described rule model is the artificial rule arranged.
19. device according to claim 12, it is characterised in that:
Content, the environmental information of user's input and the input behavior that described information acquisition unit is additionally operable to gather in user thesaurus;
Content, the environmental information of user's input and the input behavior that described analytic unit is additionally operable to analyze in the described dictionary collected, compare with the feature that can characterize user interest preserved in preset features table, and record and the feature that matches of feature in mark sheet;
Described judging unit is additionally operable to determine, according to the feature recorded, the auxiliary lexicon needing to load.
20. device according to claim 12, it is characterised in that also include:
Event responds unit, for recommending or automatically loading the described auxiliary lexicon needing and loading.
21. device according to claim 20, it is characterised in that also include:
Account management unit, for user bound, and is saved in server by the relevant information loading auxiliary lexicon; Described relevant information comprises the auxiliary lexicon list of loading and/or entry list and/or auxiliary lexicon service condition.
22. an input method system, it is characterised in that including:
Information acquisition unit, for gathering the input information of user, described input information includes the content in the list entries of user, user thesaurus, the environmental information of user's input and input behavior;
Analytic unit, for analyzing the list entries of the described user collected, compares the feature that can characterize user interest preserved in list entries and preset features table, and records and feature that feature in mark sheet matches;
Judging unit, for determining the auxiliary lexicon needing to load according to the feature recorded;
Event responds unit, for recommending or automatically loading the described auxiliary lexicon needing and loading.
23. system according to claim 22, it is characterised in that described judging unit includes:
Triggers unit, is used for judging whether to meet trigger condition;
First performs subelement, for determining the auxiliary lexicon needing to load according to the feature recorded.
24. system according to claim 22, it is characterised in that described judging unit includes:
Statistics subelement, for adding up the feature recorded;
Second performs subelement, for determining the auxiliary lexicon needing to load according to statistical result.
25. system according to claim 24, it is characterised in that:
The feature recorded is added up by described statistics subelement based on preset statistical model; Described statistical model is the weight vectors of several features.
26. system according to claim 24, it is characterised in that:
The feature recorded is added up by described statistics subelement based on preset rule model; Described rule model is the artificial rule arranged.
27. system according to claim 22, it is characterised in that also include:
Account management unit, for user bound, and is saved in server by the relevant information loading auxiliary lexicon; Described relevant information comprises the auxiliary lexicon list of loading and/or entry list and/or auxiliary lexicon service condition.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810117750.1A CN101645065B (en) | 2008-08-05 | 2008-08-05 | Determine the method for the auxiliary lexicon needing loading, device and input method system |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810117750.1A Division CN101645065B (en) | 2008-08-05 | 2008-08-05 | Determine the method for the auxiliary lexicon needing loading, device and input method system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101645088A CN101645088A (en) | 2010-02-10 |
| CN101645088B true CN101645088B (en) | 2016-06-01 |
Family
ID=41656953
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810117750.1A Active CN101645065B (en) | 2008-08-05 | 2008-08-05 | Determine the method for the auxiliary lexicon needing loading, device and input method system |
| CN200910137634.0A Active CN101645088B (en) | 2008-08-05 | 2008-08-05 | Determine the method for auxiliary lexicon, device and the input method system that need to load |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810117750.1A Active CN101645065B (en) | 2008-08-05 | 2008-08-05 | Determine the method for the auxiliary lexicon needing loading, device and input method system |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN101645065B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102346731B (en) | 2010-08-02 | 2014-09-03 | 联想(北京)有限公司 | File processing method and file processing device |
| US9626429B2 (en) * | 2010-11-10 | 2017-04-18 | Nuance Communications, Inc. | Text entry with word prediction, completion, or correction supplemented by search of shared corpus |
| CN103389979B (en) * | 2012-05-08 | 2018-10-12 | 深圳市世纪光速信息技术有限公司 | Recommend system, the device and method of classified lexicon in input method |
| CN102929401A (en) * | 2012-09-27 | 2013-02-13 | 百度国际科技（深圳）有限公司 | Method and device for processing input method application resource or function based on input behavior |
| CN103870000B (en) * | 2012-12-11 | 2018-12-14 | 百度国际科技（深圳）有限公司 | The method and device that candidate item caused by a kind of pair of input method is ranked up |
| CN104156365B (en) * | 2013-05-14 | 2018-05-11 | 中国移动通信集团湖南有限公司 | A kind of monitoring method of file, apparatus and system |
| CN103399890B (en) * | 2013-07-22 | 2016-10-26 | 百度在线网络技术（北京）有限公司 | At the method and apparatus that input method client collects words |
| CN103870553B (en) * | 2014-03-03 | 2018-07-10 | 百度在线网络技术（北京）有限公司 | A kind of input resource supplying method and system |
| CN104133855B (en) * | 2014-07-11 | 2017-12-19 | 中安消技术有限公司 | A kind of method and device of input method intelligent association |
| CN104765609B (en) * | 2015-04-03 | 2018-12-07 | 安一恒通（北京）科技有限公司 | Software context resource recommendation method, acquisition methods and corresponding device |
| CN107346182B (en) * | 2016-05-05 | 2021-11-02 | 北京搜狗科技发展有限公司 | Method and device for constructing user word bank |
| CN106896932B (en) * | 2016-06-07 | 2019-10-15 | 阿里巴巴集团控股有限公司 | A kind of candidate's words recommending method and device |
| CN106293119A (en) * | 2016-07-29 | 2017-01-04 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus carrying out information recommendation in input method |
| CN108536480B (en) * | 2017-12-28 | 2021-05-28 | Oppo广东移动通信有限公司 | Input method configuration method and related product |
| WO2020047709A1 (en) * | 2018-09-03 | 2020-03-12 | 华为技术有限公司 | Candidate word searching method for chinese input method, terminal, and server |
| CN110222256B (en) * | 2019-05-06 | 2021-10-22 | 北京搜狗科技发展有限公司 | Information recommendation method and device and information recommendation device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1089375A (en) * | 1992-12-31 | 1994-07-13 | 陈劲松 | " frequent association environment " word input method |
| CN1490701A (en) * | 2002-10-15 | 2004-04-21 | 英业达股份有限公司 | Inputting method system with dynamic adjustable lexicon and method thereof |
| CN101051323A (en) * | 2007-05-22 | 2007-10-10 | 北京搜狗科技发展有限公司 | Character input method, input method system and method for updating word stock |
-
2008
- 2008-08-05 CN CN200810117750.1A patent/CN101645065B/en active Active
- 2008-08-05 CN CN200910137634.0A patent/CN101645088B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1089375A (en) * | 1992-12-31 | 1994-07-13 | 陈劲松 | " frequent association environment " word input method |
| CN1490701A (en) * | 2002-10-15 | 2004-04-21 | 英业达股份有限公司 | Inputting method system with dynamic adjustable lexicon and method thereof |
| CN101051323A (en) * | 2007-05-22 | 2007-10-10 | 北京搜狗科技发展有限公司 | Character input method, input method system and method for updating word stock |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101645065A (en) | 2010-02-10 |
| CN101645088A (en) | 2010-02-10 |
| CN101645065B (en) | 2016-02-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101645088B (en) | Determine the method for auxiliary lexicon, device and the input method system that need to load | |
| CN109766540B (en) | General text information extraction method and device, computer equipment and storage medium | |
| CN108647205B (en) | Fine-grained emotion analysis model construction method and device and readable storage medium | |
| CN108829822B (en) | Media content recommendation method and device, storage medium and electronic device | |
| CN112632385A (en) | Course recommendation method and device, computer equipment and medium | |
| CN101470732B (en) | Auxiliary word stock generation method and apparatus | |
| CN110888990B (en) | Text recommendation method, device, equipment and medium | |
| CN107818781A (en) | Intelligent interactive method, equipment and storage medium | |
| CN107330011A (en) | The recognition methods of the name entity of many strategy fusions and device | |
| CN105956053B (en) | A kind of searching method and device based on the network information | |
| CN111324771B (en) | Video tag determination method and device, electronic equipment and storage medium | |
| CN110413988A (en) | Method, apparatus, server and the storage medium of text information matching measurement | |
| CN101382946A (en) | Information processing apparatus, information processing method, and program | |
| CN103870000A (en) | Method and device for sorting candidate items generated by input method | |
| CN114661872B (en) | Beginner-oriented API self-adaptive recommendation method and system | |
| CN112671985A (en) | Agent quality inspection method, device, equipment and storage medium based on deep learning | |
| CN110147494A (en) | Information search method, device, storage medium and electronic equipment | |
| CN111078546A (en) | Method for expressing page features and electronic equipment | |
| KR102206781B1 (en) | Method of fake news evaluation based on knowledge-based inference, recording medium and apparatus for performing the method | |
| CN110852071A (en) | Knowledge point detection method, device, equipment and readable storage medium | |
| JP5302614B2 (en) | Facility related information search database formation method and facility related information search system | |
| CN110516062A (en) | A kind of search processing method and device of document | |
| CN113220847A (en) | Knowledge mastering degree evaluation method and device based on neural network and related equipment | |
| CN114253990A (en) | Database query method and device, computer equipment and storage medium | |
| CN117370190A (en) | Test case generation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |