DE102007014405A1 - Method for word recognition in character sequences - Google Patents

Abstract

In the method according to the invention for word recognition in sequences of N characters, one or more of which may be ambiguous, a memory (15), a display (13) and a processor device (12) are used. The memory contains n-grams (strings of length n) and frequency values associated with the strings, the frequency value of an n-gram being the total number of all n-grams in a speech sample used for word recognition. The display (12) displays selected n-grams and / or recognized words, the processor device (12) being connected to the memory (15) and the display (13). From a considered sequence of characters, a list L of words of N characters is created, which can be formed from the N-character sequence, taking into account the ambiguities of the individual characters contained therein. From the list L of possible words, all words whose word probability is zero are removed, the word probability p = Pi pn being determined from the n-grams contained in the character sequence with n = 1 to N-1. From the display, the remaining words (14) of the list L of possible words are displayed.

Description

The The invention relates to a method for word recognition in sequences of N characters, of which one or more characters are ambiguous can.

The electronic recording of texts and speech is now routine become. However, it is not bug free, takes too long, requires too much memory or is not flexible enough in terms of the used devices or languages.

• O(2) = {a, ä, b, c}
• O(3) = {d, e, f}
• O(4) = {g, h, i}
• O(5) = {j, k, l}
• 0(6) = {m, n, o, ö}
• O(7) = {p, q, r, s, ß}
• O(8) = {t, u, ü, v}
• O(9) = {w, x, y, z}

ergeben sich für das Wort "baumhaus" (Ziffernfolge 22864287) 4·4·4·4·3·4·4·5 = 61.440mögliche Buchstabenkombinationen, wenn für jeden Buchstaben des eingegebenen Wortes jede Taste nur einmal gedrückt wird. Diese Buchstabenkombinationen gehen von "aatmgatw" über "baumhaus" bis "ccvöicvß". Unter diesen müssen unmögliche Kombinationen wie "ääüöiäüq" (ebenfalls Ziffernfolge 22864287) ausgeschlossen werden und eine sinnvolle Liste von möglichen Wörtern (Hypothesen) angeboten werden, z. B. für die Ziffernfolge 343 "die", "ehe", "eid", wobei die erstgenannte Möglichkeit am häufigsten vorkommt. Dies ist die Aufgabe von Worterkennungsverfahren.The electronic recording of texts and language is used, for example. For example, when entering text in keyboards. The most efficient and common is the normal computer keyboard, which provides a key or defines a key combination for each character to be entered or for each character to be entered. Other keyboards have fewer keys, such as mobile phone keyboards for sending text messages or PDAs for appointment input, special keyboards such as QWERTY keyboards, keyboards for the disabled or special purpose keyboards. When entering text into such keyboards, it is necessary to multiple assignments of the keys, so that the keys usually have to be pressed several times to activate the desired letter (Mulitap method). In the case of a conventional mobile phone z. For example, there is a common key for A BC Ä 2, and when the word "Baumhaus" is entered, for example, the key sequence 222886442887777 must be pressed (indicated in numbers), which then yields a unique word. Assuming a common German edition alphabet without case

• O (2) = {a, ä, b, c}
• O (3) = {d, e, f}
• O (4) = {g, h, i}
• O (5) = {j, k, l}
• 0 (6) = {m, n, o, ö}
• O (7) = {p, q, r, s, ß}
• O (8) = {t, u, u, v}
• O (9) = {w, x, y, z}

arise for the word "tree house" (number sequence 22864287) 4 · 4 · 4 · 4 · 3 · 4 · 4 · 5 = 61,440 possible letter combinations, if for each letter of the entered word each key is pressed only once. These letter combinations go from "aatmgatw" to "baumhaus" to "ccvöicvß". Among them, impossible combinations such as "ääüöiäüq" (also numbered 22864287) must be excluded and a meaningful list of possible words (hypotheses) offered, eg. For example, for the number sequence 343 "the", "marriage", "eid", the former possibility occurring most frequently. This is the task of word recognition.

at the voice input there are also ambiguities, for example for difficult sounds like "s" and "f", their formant frequencies mostly outside of 3.4 kHz (upper Limit of the telephone transmission frequency). Also can give it different spellings to the same phoneme d. H. when it is written, as it is spoken, attribution and selection decisions to (/ f / → f, v, ph, / a / → a, aa, ah). There are already phoneme dictionaries for Use came.

Also for example, when reading electronic text files, such as when contain this typed text or language or it is digital Documents can be virtually comparable Problems in recognizing these files will result until the words are dissolved.

The following description of the state of the art and the invention refers mainly to the text recognition when typing in keyboards for which the invention first was provided. However, the invention is not limited to this field of application limited, but also on the above and other areas of text recognition and analysis or speech recognition applicable.

For word recognition, various character disambiguation methods have been used to correct the ambiguities. Some are based on the use of so-called n-grams, ie of contiguous character sequences with n characters. n-grams have been used in the analysis of large amounts of data on specific contexts (or phrases), for example, by the intelligence service, such as the search of emails on selected subject areas, etc. They also serve to Satzerken due to given word sequences, the n-grams in this context. In the case of word recognition by means of n-grams, character sequences (also: strings) are compared with n-grams, which can have different lengths. A combination of n-grams of different lengths has proven to be useful, with the shorter n-grams providing alternative predictions and the longer n-grams providing greater uniqueness, but requiring a large memory such that n> 6 does not occur in practice. The different lengths of the n-grams take into account the frequencies of the individual letters, bigrams, trigrams and even short words. The disadvantage of using the n-gram method is that the documents are only very short. Great attention has been given to the 1992 publication "Probalistic Character Disambiguation for Reduced Keyboards Using Small Text Samples" by JL Arnott and MY Javed, AAC Augmentative and Alternative Communication, Vol. 8, pages 215 to 223 found.

If, for example, the word "tree house" is decomposed into n-grams of lengths 2 to 5, the following n-grams Vn (baumhaus) result: n = 2 V2 (tree house) = {ba, au, um, mh, ha, au, us} n = 3 V3 (Baumhaus) = {construction, aum, umh, mha, hau, aus} n = 4 V4 (tree house) = {tree, aumh, umha, mhau, house} n = 5 V5 (tree house) = {tree, aumha, umhau, mhaus}

The following frequencies are counted for some selected n-grams:
W2 (au) = 2
W3 (aum) = 1
W4 (tree) = 1
W5 (tree) = 1
Of course, n-grams that were not observed have a frequency of 0, e.g. B. W3 (lqü) = 0.

All known words of a language can now be composed of n-grams. Overall, there are z. For example, in German (excluding case sensitive), 30 letters, which limits the maximum number of possible n-grams: n = 2 900 n = 3 27,000 n = 4 810000 n = 5 24,300,000

at the special application mobile phone of intelligent text systems, without the use of text input according to the multitap method, There are only a few developments introduced in the market.

Very common is the T9 method of the company Tegic Communications, Inc. for the disambiguation of input character sequences, which in the US Pat. No. 6,307,549 B1 is described. A plotted character sequence is compared with stored vocabulary or word modules for correspondence. If there are several alternatives, these are presented in a selection list and an alternative selected by the user. For the vocabulary or word modules, a tree data structure can be provided. Each node of this structure represents a particular input character sequence, from which branch off several alternative sequences or possible ASCII character strings which are defined on the basis of a fixed key assignment. Where there is no path between nodes, there is no valid character sequence. For the expansion of the vocabulary an extra dictionary is provided. The disambiguation principle is therefore also referred to as dictionary-based disambiguation.

The US 2002/0183100 A1 describes a method for character selection when entering, for example, SMS messages. In the display, a character which statistically has the highest probability as a secondary character is respectively displayed as a sequence character depending on the preceding input, ie the already entered character sequence. The already entered string is fixed and will not be varied. The following character is calculated using a statistical database. Dictionaries are used for character selection, of which one contains word beginnings and words with up to three characters, the other words with four characters or more. Methods of this type are referred to as prefix-based disambiguation.

Also uses a statistical approach for the subsequent letter in the EP 0 924 594 A2 described method in which a two-dimensional table on the basis of a preceding Letter as well as on a three-dimensional trigram table on the basis of two preceding letters.

Also in the disambiguation method according to WO 2004/003953 A1 (eZiText method of Zi Corporation of Canada, Inc.) the first two letters of a word are clearly entered and confirmed by the user. At the beginning of the word, the frequencies of bi- and trigrams are used. The prediction is based on a user dictionary, which preferably contains whole words and their frequency.

From the EP 1 710 668 A1 is a disambiguation method is known in which a memory with words and also n-gram objects and their frequencies is used. The n-gram objects may be words or parts of words and include mono-, bi- and trigrams.

Of the Invention is based on the object, a method for word recognition to create in character sequences that are suitable for use is suitable for character ambiguities and in which the word recognition done quickly.

These Task is according to the invention in a method solved with the features of claim 1. advantageous Further developments of the method according to the invention are the subject of the dependent claims.

at the method according to the invention for word recognition in sequences of N characters, one or more of them ambiguous Thus, a memory, an ad and a uses a processor device. The memory contains n-grams (strings of length n) and strings associated frequency values, where as the frequency value of an n-gram the total number of all n-grams in one for the word recognition language sample used is used. The Display shows selected n-grams and / or recognized words wherein the processor means is connected to the memory and the display connected is. A considered character sequence becomes a list L created from words with N characters coming from the N character sequence taking into account the ambiguities of this contained individual characters can be formed. Out the list L of possible words all words are removed whose word probability is zero, where the word probability p = Π pn from the n-grams contained in the character sequence with n = 1 to N - 1 is determined. From the ad the remaining words of the list L of possible Words displayed.

One significant advantage of the method is that it is independent of the language used and key assignment Assignment problems of strings and sequences solves, resulting in meaningful word hypotheses. This is because no words but n-grams used to do word recognition in strings. The list of probable word hypotheses will appear after each keystroke when entering a word newly generated, so that one with the tap step sustained continuous updating of the hypotheses. From this list, if it contains more than one word hypothesis, the user can choose his correct word if he has the word already completely typed. The way the selection is realized, is arbitrary. If the word is not completely typed yet, the user will continue to enter new characters.

The Detection method according to the invention can any languages, legal, technical areas, etc. applied by integrating the respective vocabulary into the statistics becomes. Also the assignment of letters or other characters too the keys, d. H. the output alphabets, or key assignments are freely selectable without any changes or adjustments to the procedure become necessary. Already used Language samples can be taken over unchanged be, d. H. once a language sample can be created without effort transferred to devices with other key arrangements or assignments become. The adaptation to any languages with their individual Characters like the accent in French, Hebrew, Cyrillic, Greek etc. characters can easily be used become. The counting of a complete language sample only takes a few minutes.

The Method according to the invention is able to under competing signs (letters due to keystroke or Phonemes due to speech input or digital records) and the resulting ambiguity possible words to isolate, which is a valid or meaningful word can. It will be typed or spoken every time Letters permute the possible recognized single letters, and with each added letter can then again result in other ambiguities that are resolved.

For word chains without gaps, it can when applying the method according to the invention the word strings give ambiguities, where valid resolutions result when all of the resulting words are either valid whole words or are valid words and at the same time have a valid word beginning or a valid word end. This is illustrated by the following example, which uses the following labels:
(G) valid whole word
(W) valid word beginning, valid word end, valid words in the sense of pA, pE, pW (explained later)
(X) neither (G) nor (W), ie invalid word

Example: the weather is excellent resolution attempts:

at the application of the method according to the invention Typing usually uses a keyboard includes the keys associated with a plurality of characters, and which is connected to the processor device. When entering text The N-character sequences accordingly become a word-recognition method applied, which works according to the invention.

If the inventive method for the Voice input is used, a voice recorder used and in the voice input of the phonemes or phoneme sequences a conversion into N-character sequences, in particular of Text characters. The N-character sequences are word-coded applied, which works according to the invention.

The inventive method can be also advantageous when reading, for example, digitally available Apply text documents with character sequences. For this purpose, a reading unit used for capturing the N-character sequences and at a word recognition method is used to read the N-character sequences. Through the invention, words can be stored in the Character sequences found very quickly and reliably and be identified.

In an advantageous variant of the method according to the invention, the words from the speech sample whose length corresponds to the n-gram length are determined as whole-word n-grams, and when displaying the remaining words of the list L, first all words are sorted according to the whole-word Probability pG = GN / NG is indicated, where GN is the whole word n-gram frequency and NG is the total number of all word n-grams of the speech sample. Thus, the whole-word n-grams are mostly short words that act like a lexicon for short words taking into account the frequency of occurrence, and a meaningful sorting of word hypotheses for short words of goodness (such as "the", "marriage", "oath") support. In the case of a language sample with the words "tree house", "hello", "you", "der" the bigram "you", trigram "the" and the 5-gram "hello" and as whole word n-grams result
G2 (du) = 1, G3 (der) = 1, G5 (hello) = 1

Not observed n-grams have the frequency 0, z. B. G3 (lqü) = 0. In the speech sample, the total numbers NG (n) of all Whole word n-grams calculated. These result from the sum of all frequencies the whole word n-grams of the respective length.

In an advantageous embodiment of the method according to the invention as Wortan fangs-n-grams determine the n-grams that form the beginning of a word. The beginning-of-word probability pA = Π An / NA is determined, where An is the beginning of word n-gram frequency and NA is the total number of all word-beginning n-grams of the speech sample. In displaying the remaining possible words, all words are first sorted by the whole-word probability pG = GN / NG, where GN is the whole-word n-gram frequency and NG is the total number of all-word n-grams of the speech sample and the sort after pA pW.

In the case of the mentioned language sample with the words "tree house", "hello", "you", "der" the bigrams "ba", "ha", "you", de ", the trigrams" construction "," hal "," the, the 4-gramme "tree", "hall" and the 5-gramme "baumh" as well as "hello" .Thus, the following frequencies of the word beginning n-grams result: A2 (ba) = 1 A2 (ha) = 1 A2 (du) = 1 A2 (en) = 1 A3 (construction) = 1 A3 (hal) = 1 A3 (the) = 1 A4 (tree) = 1 A4 (hall) = 1 A5 (tree) = 1 A5 (hello) = 1

Prefers Word-end n-grams are also used, where as word-end n-grams the n-grams are determined, which form the end of a word. The word end probability pE = Π En / NE is determined where En is the word end n-gram frequency and NE is the total number all word end n-grams of the speech sample is. At the display the remaining possible words become first all words sorted by the whole word probability pG = GN / NG and the word-beginning n-gram probability pA = Π An / NA where GN is the integer n-gram frequency, NG the total number of all word n-grams of the speech sample is At the word beginning n-gram frequency and NA the total number of all Word sample n-grams of the language sample is and the sorting after pA · pW · pE.

In the case of the mentioned language sample with the words "house", "hello", "hello", "you", "der", the bigrams "us", "lo", "you", "he" result as the word end n-grams ", Trigrams" from "," llo "," the ", 4-gramme" house "," allo "and the 5-gramme" mhaus "," hello ".This results in the following frequencies: E2 (us) = 1 E2 (lo) = 1 E2 (du) = 1 E2 (er) = 1 E3 (off) = 1 E3 (llo) = 1 E3 (der) = 1 E4 (house) = 1 E4 (allo) = 1 E5 (mhaus) = 1 E5 (hello) = 1

Advantageous is in the inventive method for an N-character sequence with each additional character entered Word list L recreated, d. H. there is a continuous Updating the hypotheses. From list L, if more than contains a word hypothesis, the user can get the correct word if he already typed the word completely. As the Selection from a proposal offer is realized, is arbitrary.

In the previous explanations were for the n-grams Values of n = 2, n = 3, n = 4, n = 5 are used. These values are not fixed rigidly but can according to the circumstances be adjusted. Preferably, when using the inventive Method for the n-grams values of n = 2, n = 3 used for the storage requirements significantly lower than in the case is longer n-grams. It can depending on the application also n-grams with n = 1 (ie individual letters) are used.

Prefers Values of n = 4 and / or n are also used for the n-grams = 5 used. The longer the maximum n-grams selected (i.e., larger maximum values for n), the better the proposed word hypotheses. It will but also more extensive language samples necessary.

in the Memory can be a list of characters or character sequences and of these associated exchange characters, exchange character sequences or exchange n-grams. This is done in this way an adaptation to the habits of a user, certain characters or words (eg "sparrow" and not "rick"), certain short forms (English: "dont" → "do not", French: "cest" → "c'est"), to use special characters (eg smileys), to a special vocabulary etc .. The short forms must but then also entered in their short form in the language sample with become.

It may also be expedient to supplement the n-grams in the memory in order to enable the recognition of new words or special entries. The input of unknown words is not necessary. Sufficient is the updating of corresponding n-grams (Wortanfang-n-Gram me, word-n-grams, word-end-n-grams, whole-word-n-grams). It does not make sense to store all possible frequencies of the n-grams An (∙), Wn (∙), En (∙) and Gn (∙) (eg, for n = 5, there are over 24 million possible n-grams). programs). This is not necessary either. Only a few of these n-grams occur in the language, ie the frequency of most n-grams is 0. Their storage can be omitted.

Wortend-n-grams bring the statement that it is a valid one complete word, and other features can be found in the Meaning of the acquired speech data recognize a word as such. To the isolate individual words, it is especially for Applications with reading files also useful if word boundaries, In particular, word ends, additionally entered to the word string into individual complete words, eg. B. "tree house" also in "tree house" to share.

The inventive method can also with a Be equipped word prediction. This can be done so that based on an input N-character sequence a word recognition for a character sequence with an assumed length of N + (1 to l) characters, where l is the prediction length, d. H. the number of predicted entry steps is. After creation the list L is created from this another list L ', the contains all the words in list L, these words to characters or character sequences with the length 1 to l are supplemented. The list L 'becomes all words removed, whose word probability is zero in the list L 'remaining words will be sorted and the words the Lists L and L 'are displayed. This way can for a not yet fully entered word a prediction Then, which word or words are taken the user has in mind when entering.

expedient in this word prediction method, the list L 'first all words after the whole word probability pG = GN / NG where GN is the whole-word n-gram frequency and NG is the total number of all word n-grams of the speech sample. The sorting then takes place after the start word n-gram and the End-word n-gram probability after pA · pW · pE.

In the above, the determination of the n-grams and their use are explained Service. The following is a representation of the determination of the word probabilities.

The language statistics included in the various n-gram groups are used to exclude, on the one hand, word hypotheses that are most likely not a word of the current language and, on the other, to put the remaining hypotheses in order according to their probable correctness. In the following, w = w1w2w3... WN denotes a word w of length N, composed of the letter sequence w1w2w3... WN. The following occurrence probabilities are determined:
For a word w, the probabilities that w is a valid word in terms of n-grams of length n are calculated

From these n-gram-length word probabilities, an entire word probability of the word w can be calculated for the total of all trained n-gram lengths:

As soon as even only one of the word-n-gram frequencies Wn (∙) = 0, is also the word probability pW (w) = 0.

At the Example of the word "Baumhaus" will be explained further.

For the determination of bigrams and assuming that there are a total of NW (2) = 100 bigrams, we obtain: p2W (Baumhaus) = W2 (ba) / NW (2) * W2 (au) / NW (2) * W2 (um) / NW (2) * W2 (mh) / NW (2) * W2 (ha) / NW (2) * W2 (au) / NW (2) * W2 (us) / NW (2) = 1/100 * 2/100 * 1/100 * 1/100 * 2/100 * 2/100 * 1 / 100

For trigrams follows: p3W (tree) = W3 (construction) / NW (3) * W3 (aum) / NW (3) * W3 (umh) / NW (3) * W3 (mha) / NW (3) * W3 (hau) / NW (3) · W3 (off) / NW (3)

From these results ultimately results pW (Baumhaus) = ... · p2W (Baumhaus) · p3W (Baumhaus) · ...

A great help in assessing whether there is a word w are the word-beginning probabilities. For if there are no words in the language sample with the word-beginning n-grams of the word w, this will most likely not be a valid word of the language. Accordingly, the probability that a word w exists in the sense of the beginning of the word is calculated

As soon as even just one of the word-beginning n-gram frequencies An (∙) = 0 is also the word beginning probability pA (w) = 0.

An example will explain this in more detail. Suppose that you want to calculate the word beginning probability for n-grams of length 2 to 5 and the word w = tree. Given the frequencies from the list of top-of-the-word bigrams illustrated above, which in this example always has the value 1. Some exemplary total numbers of word beginning n-grams are NA (2) = 12, NA (3) = 10, NA (4) = 13, NA (5) = 11. This yields pA (tree) = A2 (ba) / NA (2) * A3 (construction) / NA (3) * A4 (tree) / NA (4) * A5 (tree) / NA (5) = 1/12 * 1 / 10 · 1/13 * 1 / 11th

Another great help in assessing if there is a word w is, as mentioned, the word end probabilities. If there are no words in the language sample that end in the same string of letters as the word w, then this is probably not a word of the language. The word end probabilities can be calculated directly from the word end n-grams:

As soon as even just one of the word end n-gram frequencies En (∙) = 0 is also the word end probability pE (w) = 0.

One Unknown word ending does not necessarily indicate a nonsensical word hypothesis but can just as well be an indication that a word is not completely entered yet.

This is illustrated by the following example: Assume that the word end probability for n-grams of length 2 to 5 and the word w = tree is to be calculated. Given the frequencies from the list of word end bigrams illustrated above, which are always 1 in this example, and some example total numbers of word end n grams are NE (2) = 22, NE (3) = 20, NE (4) = 23, NE (5) = 21. This yields pE (tree house) = E2 (us) / NE (2) · E3 (off) / NE (3) · E4 (house) / NE (4) · E5 (mhaus) / NE (5) = 1/22 · 1 / 20 · 1/23 · 1/21

The following applies to the whole-word probabilities: If the word w to be evaluated is so short that whole-word n-grams of the same length have been determined from the speech sample, the occurrence probability of w can be simply specified as pG (w) = GN (w1 ... wN) / NG (N)

An example will explain this in more detail. Suppose that the whole-word probability is calculated for the words w = der, w = du and w = lqü. Given the frequencies from the above-mentioned speech sample (always 1 or 0) and some exemplary total numbers of whole-word n-grams, let NG (2) = 33, NG (3) = 30. This yields pG (der) = G3 (der) / NG (3) = 1/30 pG (du) = G2 (der) / NG (2) = 1/33 pG (lqü) = G3 (der) / NG (3) = 0/30

It The concrete procedure will now become closer with the example of "Baumhaus" described to the variety of possible character combinations for a word (here as already stated above: 61.440) to create a meaningful list of word alternatives.

Out the list of possible words becomes all words whose probabilities pW (w) = 0 or pA (w) = 0 are removed. These words are almost certainly not correct Word dar. For performance reasons, it makes sense already in building the first word list L apply this criterion and at all only add words to the list for which pW (w) ≠ 0 and pA (w) ≠ 0.

• (a) Zuerst stehen alle Wörter mit pG(w) ≠ 0, absteigend sortiert nach pG(w). Damit bekommen Wörter Priorität, für die Ganzwort-n-Gramme vorhanden sind.
• (b) Danach kommen alle Wörter mit pE(w) ≠ 0, absteigend sortiert nach pA(w)·pW(w)·pE(w). Damit bekommen Wörter, die ein komplettes Wort repräsentieren, Priorität vor solchen, die (bisher) nur teilweise eingegeben sind.
• (c) Es folgen alle restlichen Wörter, absteigend sortiert nach pA(w)·pW(w). In Vergleich zu der vorhergehenden Wortgruppe aus (b) werden Wörter hinten angestellt, die erst teilweise eingegeben sind. Sinnvoll wäre, dass die Eingabe von 2286428 als Hypothese zwar das Teil-Wort "baumhau" findet, aber eventuell bessere Hypothesen bevorzugt, die nach (b) bereits ein gesamtes Wort repräsentieren.

From the few remaining word hypotheses a sorted list is generated, whereby the order of the individual words results from the following three criteria:

• (a) First all words with pG (w) ≠ 0 are listed, sorted in descending order according to pG (w). This gives priority to words for which whole-word n-grams exist.
• (b) Then all words come with pE (w) ≠ 0, sorted in descending order according to pA (w) · pW (w) · pE (w). This gives words that represent a complete word priority over those that are (so far) only partially entered.
• (c) All remaining words follow, sorted in descending order by pA (w) · pW (w). Compared to the previous word group from (b), words are placed behind, which are only partly entered. It makes sense that the entry of 2286428 as a hypothesis, although the sub-word "tree" finds, but may prefer better hypotheses, which after (b) already represent an entire word.

The Invention will be described below with reference to exemplary embodiments and further explained the drawing. In the drawing show:

1 a processor device for carrying out the method according to the invention when entering text into a keyboard,

2 a processor device for carrying out the method according to the invention in voice recording,

3 a flow chart of the method according to the invention for word recognition,

4 a flow chart to supplement the n-grams in memory and

5 a flow chart for the prediction of words in already entered subwords.

1 shows a processor device including peripherals, with which the inventive method can be used in the text input. A keyboard 10 with buttons 11 , an ad 13 and a memory 15 are to a processorein direction 12 connected. The keys 11 the keyboard 10 are assigned several characters, so that the character input is not immediately uniquely identifiable strings, words, etc. arise. The memory 15 contains n-grams and frequency values associated with these n-grams, denoted by the reference numeral 16 are symbolized. The screen display 14 the ad 13 illustrates the remaining words determined using the stored n-grams and their frequency values as possible words, here the three alternative words "the", "marriage", "eid".

In 2 a processor device is shown with peripherals for the word recognition in the voice recording. A voice recorder like a microphone 20 , an ad 13 and a memory 15 are with a processor device 21 connected. In the speech input, uniquely unambiguously identifiable phonemes or derived graphemes, N-character sequences of strings or words, etc. are not immediately generated. Basically, the approach is analogous to that in text input. The memory 15 contains n-grams and frequency values associated with these n-grams, denoted by the reference numeral 16 are symbolized. The screen display 14 the ad 13 illustrates the remaining words determined using the stored n-grams and their frequency values as possible words, here the three alternative words "the", "marriage", "eid".

3 shows that the method for word recognition is essentially characterized by the following method steps. In step 101 the procedure is the current state of the input, z. A sequence of N keystrokes. From this input is in step 102 the list L of all possible word hypotheses based on the existing input ambiguities generated by permutation of all possible combinations. In the process step 103 For example, the whole-word probabilities pG, the word probabilities pW, the end-of-word probabilities pE, and the beginning-of-word probabilities pA are computed for each word hypothesis of the list L. Based on these probabilities will be in the process step 104 removes from the list L all word hypotheses whose word probabilities pW or word-beginning probabilities pA are zero and which therefore do not represent a valid word with great certainty. If a word prediction is to be performed, the query branches 112 for the production of in 5 illustrated and explained in more detail below creation of the prediction list L '. If valid whole words exist in the list L, characterized by hypotheses with non-zero integer probabilities, the query branches 105 in the process step 106 , the all valid whole words, sorted in descending order of their whole word probabilities, on the display 14 represents. step 107 removes all in the process step 106 displayed hypotheses from the list L, thus avoiding the multiple output of the same hypothesis. If valid complete words exist in the list L, characterized by hypotheses with non-zero word end probabilities, the query branches 108 in the process step 109 , the complete valid words, descending sorted by the product of their word-end-probabilities, word-beginning-probabilities and word-probabilities, to the previous edition on the display 14 appends. step 110 removes all in the process step 109 displayed hypotheses from the list L, thus avoiding the multiple output of the same hypothesis. All remaining hypotheses of the list L are in the process step 111 , descending sorted by the product of their word-beginning probabilities and word probabilities, to the previous output on the screen 14 added. If a word prediction is to be performed, the query branches 112 for the output of the list L ', added to the previous edition on the screen 14 , If the user accepts one of the displayed words, the query branches 115 to process step 116 which provides the selected word to any application and deletes the current character sequence so that upon the next input, the method of FIG 3 in step 101 begins with an empty character sequence, ie a new word.

The appropriate embodiment of the supplement of the memory 15 reproached n-grams by new words (unknown or accepted) is represented by the following process steps 4 , described. In the process step 201 is the basis of the complement determination of all n-grams Vn (w) of the memory 15 w to be integrated. If the word w has a length covered by the whole-word n-grams, the query branches 202 in the process step 203 which updates the frequency of the word-word-associated whole-word n-gram. In the process step 204 the word w is stored in the database of the word-in-n-grams in memory 15 integrated by updating the frequencies of the word-beginning n-grams of all n-grams Vn (w) representing valid word-beginning n-grams of the word w. In the process step 205 the word w is written to the database of the word n-grams in memory 15 integrated by updating the frequencies of the word n-grams of all n-grams Vn (w). In the process step 206 the word w is written into the database of the word end n-grams in memory 15 integrated by updating the frequencies of the word-end n-grams of all n-grams Vn (w) representing valid word-end n-grams of the word w.

5 describes the method steps for generating a word prediction list L ', referenced in 3 , Process step 114 , From a list L is in the process step 301 generates a new list L 'containing for each hypothesis of the list L all concatenation of this hypothesis with all permutations of the known output alphabet in the lengths of 1 to 1 characters. From the list L 'are in the process step 302 removes all hypotheses that have either a word probability of zero or a word-first probability of zero or a word-end probability of zero. The remaining hypotheses of list L 'are in the process step 303 sorted so that all hypotheses that represent a valid whole word and are sorted in descending order of the whole word probability pG follow the further hypotheses and are sorted in descending order of the product of their end-of-word probabilities, beginning of word probabilities, and word probabilities. The edition 304 of the prediction method is thus the sorted list L '.

in the The following is the process of the invention on the basis of concrete examples in German and Latin using a telephone keypad explained.

For first example, an extensive language sample of 688,000 words has been used contains many compound words and also books from the trivial literature. The n-gram occupancy is as follows: Table 1 Number of n-grams in the linguistic coarse n = 2 max. 900 n = 3 max. 27,000 n = 4 max. 810000 n = 5 max. 24,300,000 Word n-grams 779 (= 87%) 9,253 (= 34%) 47,853 (= 6%) 121,139 (= 0.5%) Word initial n-grams 464 (= 52%) 2,965 (= 11%) 9,303 (= 1%) 20,113 (= 0.1%) Wortend-n-grams 469 (= 52%) 2,636 (= 10%) 8,714 (= 1%) 20,535 (= 0.1%) Whole-word n-grams 125 (= 14%) 526 (= 2%) 1,614 (= 0.2%) 3,670 (= 0.01%)

At This table can be seen well, that just by the n-grams with n = 4 and n = 5 much knowledge is represented as one Large part (95% -99.99%) of all four- and five-letter combinations do not occur in the language sample.

The Word recognition procedure will now work for the words "Is" "the" "tree house" "already" "ready", "prom", "beer box", "Foreign trade turnover", "football game" on the hand of her Number sequences 478 327 22864287 72466 337844. 2272458772255, 2437527836, 287364263357867289, 387225577435 are recognized. For comparison are the results when using the T9 technology of Tegic specified.

Table 2 shows the result, with the searched or typed word shown in bold. Behind it is the respective word hypothesis list. Table 2 input Suggestions according to the invention Suggestions after T9 478 is, eats, gst, gru, grt, grü is, eats, hsv 327 that, that, bar, fas, eas, där, far, fär, fäs that, that, faq, barrel, dcs, fas, far, fäs, fär, eas 22864287 tree house (no suggestion, unknown word) 72466 already, beautiful, schno, schmo, schmö, schnö already, well, yes, schmö 337844 ready, destig, firm, festhi ready, firm 2272458772255 prom, prom abschlussackl 2437527836 beer, beer, beer, beer, beer, beer, beer, beer, beer, beer AIDSlarten (correct word unknown!) 287364263357867289 foreign trade turnover, foreign trade turnover, foreign trade turnover, foreign trade turnover (no suggestion, unknown word) 387225577435 football game football game

The Differences between the two word recognition methods lie essentially not when editing the simple, common Words. Many compound words that are when using the method according to the invention can develop with the conventional T9 method can not be found. The calculation time is Creation of the o. G. Word hypothesis list in the unmeasurable area.

The following example refers to Latin on a 6-key keyboard with the following key mapping:

• O(0) = {a, b, c, d}
• O(1) = {e, f, g, h}
• O(2) = {i, l, m, n}
• O(3) = {o, p, q, r}
• O(4) = {s, t, u}
• O(5) = {v, x, y}

The letters j, k, w, z do not appear in Latin and are therefore omitted. The example shows how easily text input can be adapted to new languages as well as other keyboards. This results in the following output alphabet:

• O (0) = {a, b, c, d}
• O (1) = {e, f, g, h}
• O (2) = {i, l, m, n}
• O (3) = {o, p, q, r}
• O (4) = {s, t, u}
• O (5) = {v, x, y}

The Language statistics were determined from a sample of language samples exclusively a series of longer Latin original texts (eg. B. Caesar "Commentary Libri VII de Bello Gallico", "Commentary Libri III de Bello Civili "," Libri Incertorum Auctorum ") with a total of 128,000 words existed.

After counting, the following are occupied by the possible n-grams: Table 3 Number of n-grams in the linguistic coarse n = 2 max. 484 n = 3 max. 10648 n = 4 max. 234256 n = 5 max. 5153632 Word n-grams 356 (= 74%) 2,696 (= 25%) 10,130 (= 4%) 19,274 (= 0.4%) Word statements-fangs-n-grams 205 (= 42%) 1,177 (= 11%) 3,049 (= 1%) 5,117 (= 0.1%) Wortend-n-grams 152 (= 31%) 931 (= 9%) 3,160 (= 1%) 6,465 (= 0.1%) Whole-word n-grams 54 (= 11%) 163 (= 2%) 540 (= 0.2%) 1280 (= 0.02%)

Out Table 3 again shows that it is precisely the n-grams with n = 4 and n = 5 a lot of information is supplied, which is the language sample itself does not contain.

In the following should
Multa legas facito, perlectis negie multa.
Qualis artifex pereo!
[Cato Maiar: "See that you read a lot and when you read it, much of it is ignored." and "What great artist is going away with me!"]
on the basis of their inputs 24240 21104 100243, 313210424 2112111 24240. 340224 0342115 31313! be recognized. The complete sorted list of hypotheses is given for each word, the correct hypothesis in bold: Table 4 input Suggestions according to the invention 24240 multa 21104 legas, legate, negat, nefas 100243 facito, habito, gadito, gadisq 313210424 perlectis, perlectit, perlectiu 2112111 neglege 24240 multa 340224 qualis, qualit, publiu, rudimu 0342115 artifex 31313 pereo, reper, peper, pereq, perfr, perfo, pergr

QUOTES INCLUDE IN THE DESCRIPTION

This list The documents listed by the applicant have been automated generated and is solely for better information recorded by the reader. The list is not part of the German Patent or utility model application. The DPMA takes over no liability for any errors or omissions.

Cited patent literature

• - US 6307549 B1 [0012]
• US 2002/0183100 A1 [0013]
• - EP 0924594 A2 [0014]
• WO 2004/003953 A1 [0015]
• - EP 1710668 A1 [0016]

Cited non-patent literature

• - "Probalistic Character Disambiguation for Reduced Keyboards Using Small Text Samples" by JL Arnott and MY Javed, AAC Augmentative and Alternative Communication, Vol. 8, pages 215 to 223 [0007]

Claims (16)

Method for word recognition in sequences of N characters, one or more of which can be ambiguous at which uses a memory, a display and a processor device become, the memory being n-grams (strings with the Length n) and frequency values assigned to the character strings contains, where as the frequency value of an n-gram the total number of all n-grams in one for word recognition used language sample is used, the ad selected n-grams and / or recognized words indicating wherein the processor means is connected to the memory and connected to the ad, in the case of a considered sequence of characters a list L of words with N characters is created that from the N-character sequence, taking into account the ambiguities which can be formed in this single character contained at from the list of possible words all Removing words whose word probability is zero, in which the word probability p = Π pn from those in the character sequence contained n-grams with n = 1 to N-1, and at the display of the remaining words of the list L of possible words are displayed. Method according to claim 1, characterized in that that applied it to a keyboard for text input becomes, the keyboard comprising keys that are multiple characters are assigned, and the keyboard connected to the processor device is and in the text input of the N-character sequences, a word recognition method is applied. Method according to claim 1, characterized in that that it is used for voice input, and in which a voice recorder is used, and in the speech input the phonemes or phoneme sequences convert into N-sign sequences, in particular of text characters, done, and on the N-character sequences Word recognition method is applied. Method according to claim 1, characterized in that that it is used for reading character sequences becomes, wherein a reading unit is used, and in which Reading the N-character sequences uses a word-matching procedure becomes. Method according to one of claims 1 to 4, characterized in that as whole-word n-grams the words be determined from the language sample, the length of the corresponds to n-gram length, and when displaying the remaining Words of the list L first all words sorted are displayed after the whole-word probability pG = GN / NG, where GN is the integer n-gram frequency and NG is the total number of all the word n-grams of the speech sample is. Method according to one of claims 1 to 4 and 5, characterized in that the word beginning n-grams the n-grams are formed, which form the beginning of a word, the Word-beginning probability pA = Π An / NA is determined, where An is the beginning word n-gram frequency and NA is the Total number of all word-beginning n-grams of the speech sample, and in displaying the remaining possible words first all words sorted by the whole word probability pG = GN / NG, where GN is the integer n-gram frequency and NG is the total number of all word n-grams of the speech sample and the sorting is done according to pA · pW, where pW = Π pnW the word probability is and pnW = Π Wn / NW, Wn the Word-n-gram frequency and NW the total number of all word n-grams is. Method according to one of Claims 1 to 4 and 5 or 6, characterized in that the n-grams which form the end of a word, the word-end probability pE = Π En / NE, are determined as the word-end n-grams, where En is the word end n-gram frequency and NE is the total number of all word end n-grams of the speech sample, and when the remaining possible words are displayed, first all words are sorted by the whole word probability pG = GN / NG and the word n-gram probability pA = Π An / NA, where GN is the whole-word n-gram frequency, NG is the total number of all full-word n-grams of the speech sample, the word-first n-gram frequency and NA the The total number of all word-beginning n-grams of the speech sample is, wherein the sort after pA · pW · pE he follows. Method according to one of claims 1 to 4 and one of claims 5 to 7, characterized in that for an N-character sequence with each further input Character the word list L is recreated. Method according to one of claims 1 to 8, characterized in that for the n-grams values of n = 2, n = 3 are used. Method according to claim 9, characterized in that that values of n = 4 and / or n = 5 are used for the n-grams become. Method according to claim 9 or 10, characterized that the value n = 1 is used for the n-grams. Method according to one of claims 1 to 11, characterized in that in memory a list of characters or character sequences and their associated replacement characters, Exchange character sequences or exchange n-grams is stored. Method according to one of claims 1 to 12, characterized in that the n-grams supplemented in the memory Be aware of recognizing new words or special entries to enable. Method according to one of claims 1 to 13, characterized in that word boundaries, in particular word ends, be entered. Method according to one of claims 1 to 14, characterized in that based on an entered N character sequence A word recognition for a character sequence with an assumed length of N + (1 to 1) characters is performed, wherein after creating the list L is created from this one more list L ', all the words contains the list L, these words being characters or character sequences of length 1 to l added are, from the list L 'all words are removed whose word probability is zero, those in the list L ' remaining words are sorted and the words lists L and L 'are displayed. Method according to claim 15, characterized in that that in the list L 'first all words after the whole word probability pG = GN / NG, where GN is the integer n-gram frequency and NG is the total number of all word n-grams of the speech sample is, and the sorting then after the start word n-gram and the End-word n-gram probability after pA · pW · pE he follows.