公开(公告)号：US07801723B2

公开(公告)日：2010-09-21

申请号：US10999792

申请日：2004-11-30

申请人： Ronald M. Kaplan ,  Richard Crouch ,  Daniel G. Bobrow

发明人： Ronald M. Kaplan ,  Richard Crouch ,  Daniel G. Bobrow

IPC分类号： G06F17/27

CPC分类号： G06F17/2745 ,  G06F17/2785

摘要： Techniques are presented to determine user-interest sensitive condensations of a passage. One or more passages are selected and user interest information, condensation transformations and optional meaning distortion constraints are identified. The foci of user interest within the selected passages are determined based the similarity of the elements in the selected passages to elements in the user interest information. The condensation transformations are applied to the selected passages to preferentially retain user foci while eliding less salient information. The resultant condensate provides signals the user-interest sensitive meaning of the passage. Meaning distortions constraints are optionally applied in conjunction with the condensation transformations or in creating the condensation transformations to reduce the likelihood of distorting the meaning of the passage.

摘要翻译： 提出技术来确定通道的用户感兴趣的浓缩。 选择一个或多个段落，并且识别用户兴趣信息，缩合转换和可选的含义失真约束。 所选段落内的用户感兴趣的焦点是根据所选段落中的元素与用户兴趣信息中的元素的相似度来确定的。 冷凝转化被应用于所选择的通道，以优先保留用户焦点，同时消除较少显着的信息。 所得到的冷凝物提供了用户对通道敏感的意义的信号。 意义上的扭曲约束任选地与缩合转换一起应用，或者用于产生缩合转化，以减少扭曲通道含义的可能性。

公开(公告)号：US07401077B2

公开(公告)日：2008-07-15

申请号：US11017890

申请日：2004-12-21

申请人： Daniel G. Bobrow ,  Ronald M. Kaplan

发明人： Daniel G. Bobrow ,  Ronald M. Kaplan

IPC分类号： G06F17/30 ,  G06F7/00

CPC分类号： G06F17/30699 ,  G06F17/30864 ,  Y10S707/99935 ,  Y10S707/99936 ,  Y10S707/99942 ,  Y10S707/99943

摘要： Techniques are provided to construct and use user-interest sensitive indicators of search results. A set of documents is determined based on one or more search terms. Passages within each selected document are identified based on the search terms. Condensation transformations applied to the passages to preferentially retain elements of the passage based on the search terms and user interest information. The resultant indicator is provides a user-interest sensitive signal of the meaning of the passage.

摘要翻译： 提供技术来构建和使用搜索结果的用户兴趣敏感指标。 一组文件是根据一个或多个搜索字词确定的。 根据搜索条件识别每个选定文档内的通行。 基于搜索项和用户兴趣信息，应用于通道的冷凝转化优先保留通道的元件。 所得到的指标提供了通道意义的用户感兴趣的敏感信号。

公开(公告)号：US07890500B2

公开(公告)日：2011-02-15

申请号：US11760953

申请日：2007-06-11

申请人： Daniel G. Bobrow ,  Ronald M. Kaplan

发明人： Daniel G. Bobrow ,  Ronald M. Kaplan

IPC分类号： G06F17/30 ,  G06F7/00

CPC分类号： G06F17/30699 ,  G06F17/30864 ,  Y10S707/99935 ,  Y10S707/99936 ,  Y10S707/99942 ,  Y10S707/99943

摘要： Techniques are provided to construct and use user-interest sensitive indicators of search results. A set of documents is determined based on one or more search terms. Passages within each selected document are identified based on the search terms. Condensation transformations applied to the passages to preferentially retain elements of the passage based on the search terms and user interest information. The resultant indicator is provides a user-interest sensitive signal of the meaning of the passage.

摘要翻译： 提供技术来构建和使用搜索结果的用户兴趣敏感指标。 一组文件是根据一个或多个搜索字词确定的。 根据搜索条件识别每个选定文档内的通行。 基于搜索项和用户兴趣信息，应用于通道的冷凝转化优先保留通道的元件。 所得到的指标提供了通道意义的用户感兴趣的敏感信号。

公开(公告)号：US5524066A

公开(公告)日：1996-06-04

申请号：US220861

申请日：1994-03-31

申请人： Ronald M. Kaplan ,  Daniel G. Bobrow

发明人： Ronald M. Kaplan ,  Daniel G. Bobrow

IPC分类号： G06K9/34 ,  G06K9/00 ,  G06K9/46 ,  G06K9/62 ,  G06K9/72

CPC分类号： G06K9/00 ,  G06K9/723 ,  G06K2209/01

摘要： A top-down technique for character text recognition of an image comprises a left-to-right analysis of each image line. A current image portion is selected. Possible text prefixes are selected from a dictionary. The upper and lower text contours of the text prefixes are compared with a bitmap of the current image portion. A distance value is generated, indicating the quality of the comparison. The prefixes are then added to an agenda of prefixes. Based on the distance value, corresponding to the similarity of the upper shapes and lower shapes of the possible prefix to the bitmap of the image portion, a list of the text prefixes generating the best distance values is selected from the agenda. From the selected list, a new list of extended text prefixes is obtained from the dictionary and added to the agenda. The process is repeated until the current image portion ends. At this point, the possible text prefix having the best total distance value is selected as the list of text characters corresponding to the image portion. The total distance value is the sum of all of the distance values of the text characters forming the text prefix. Possible text words are selected from the agenda based on beam searching techniques against either a threshold or by limiting the number of possible text prefixes selected to a predetermined number of the currently most probable text prefixes.

摘要翻译： 用于图像的字符文本识别的自顶向下技术包括每个图像行的从左到右的分析。 选择当前图像部分。 从字典中选择可能的文本前缀。 将文本前缀的上下文本轮廓与当前图像部分的位图进行比较。 产生距离值，表示比较的质量。 然后将前缀添加到前缀的议程中。 基于距离值，对应于可能前缀与图像部分的位图的上部形状和下部形状的相似度，从议程中选择产生最佳距离值的文本前缀的列表。 从所选列表中，从字典获取扩展文本前缀的新列表，并将其添加到议程中。 重复该过程直到当前图像部分结束。 此时，选择具有最佳总距离值的可能的文本前缀作为对应于图像部分的文本字符的列表。 总距离值是形成文本前缀的文本字符的所有距离值的总和。 基于针对阈值的波束搜索技术从可选文本词中选择可能的文本词，或通过限制被选择到预定数量的当前最可能的文本前缀的可能的文本前缀的数量。

公开(公告)号：US5560037A

公开(公告)日：1996-09-24

申请号：US420397

申请日：1995-04-10

申请人： Ronald M. Kaplan

发明人： Ronald M. Kaplan

IPC分类号： G06F17/26 ,  G06F15/00

CPC分类号： G06F17/26

摘要： A data structure for use in hyphenation is created by including hyphen codes at the acceptable hyphenation points of words and then collapsing the words into a minimal state determinized FSM data structure. The transitions of the data structure are sorted so that a hyphen code that has alternatives is positioned before its alternatives. The data structure is then encoded for compactness. In searching with a word, if a mismatch occurs in the branch of the data structure that depends from a hyphen code, the search continues with its alternatives, because a match could be found in a branch depending from one of the alternatives. The data structure may be accessed with a hyphenated word to check hyphenation or spelling. It may be accessed with an unhyphenated word to retrieve its hyphenation points. It may be accessed with a number corresponding to a word to retrieve that word with its hyphenation points. Retrieved hyphenation points may be used in selecting where to hyphenate a word that has more than one hyphenation point, as in justification of text.

摘要翻译： 用于连字符的数据结构是通过在可接受的单词连字符点处包含连字符码，然后将字汇集成最小状态确定的FSM数据结构来创建的。 数据结构的转换被排序，使得具有备选项的连字符代码位于其替代之前。 然后将数据结构编码为紧凑。 在使用单词进行搜索时，如果在连字符代码中依赖于数据结构的分支中发生不匹配，搜索将继续使用其替代方法，因为根据其中一个选项可以在分支中找到匹配项。 数据结构可以使用连字字来检查连字符或拼写。 可以使用未连接的单词访问它来检索其连字符。 可以使用与单词相对应的数字来访问它，以使用其连字符点来检索该单词。 检索的连字符点可用于选择在哪里连字词具有多个连字符点，如在文本的对齐中。

公开(公告)号：US5488719A

公开(公告)日：1996-01-30

申请号：US814552

申请日：1991-12-30

申请人： Ronald M. Kaplan ,  Robert Shuchatowitz ,  Atty T. Mullins

发明人： Ronald M. Kaplan ,  Robert Shuchatowitz ,  Atty T. Mullins

IPC分类号： G06K9/68 ,  G06F17/30

CPC分类号： G06K9/6807

摘要： A data storage medium stores string data that can be used in character recognition and instructions for accessing the string data. The string data includes data units that can be accessed by a processor in executing the instructions. The processor can use character data indicating characters of a string to access a sequence of the data units that ends with an ending subsequence. The ending subsequence includes acceptance information indicating whether a string whose sequence of data units ends with the ending subsequence is an acceptable string. If so, the ending subsequence also includes category set information indicating a set of categories for strings whose sequences end with the ending subsequence. The categories can include words, numbers, compound words, and so forth. The acceptance information can include a bit in a character label data unit that includes information indicating the character type of an ending character. The acceptance information can also include an acceptance data unit whose value indicates an acceptable string ending. The acceptance data unit can be followed by category data units, each with a value indicating a category. The category data units can be used to obtain a bit vector for a string, each bit of which indicates whether the string is in one of the categories. For compactness, all or part of an ending subsequence can be shared by plural acceptable strings. Looping can be used to represent a category with a potentially infinite number of strings, such as numbers.

摘要翻译： 数据存储介质存储可用于字符识别的字符串数据和用于访问字符串数据的指令。 字符串数据包括处理器在执行指令时可以访问的数据单元。 处理器可以使用指示字符串的字符的字符数据来访问以结尾子序列结束的数据单元的序列。 结束子序列包括表示数据单元的序列是否以结束子序列结束的字符串是可接受字符串的接收信息。 如果是，则结束子序列还包括指示其序列以结尾子序列结束的字符串的类别集合的类别集信息。 类别可以包括单词，数字，复合词等。 接受信息可以包括字符标签数据单元中包含指示结束字符的字符类型的信息的位。 接受信息还可以包括其值表示可接受的字符串结束的接受数据单元。 接受数据单元可以跟随类别数据单元，每个具有指示类别的值。 类别数据单元可以用于获得字符串的位向量，其每一位表示字符串是否在其中一个类别中。 对于紧凑性，结束子序列的全部或部分可以由多个可接受的字符串共享。 循环可用于表示具有潜在无限数量的字符串（例如数字）的类别。

公开(公告)号：US5438511A

公开(公告)日：1995-08-01

申请号：US260205

申请日：1988-10-19

申请人： John T. Maxwell, III ,  Ronald M. Kaplan

发明人： John T. Maxwell, III ,  Ronald M. Kaplan

IPC分类号： G06F9/44 ,  G06F17/27 ,  G06F17/28 ,  G06F17/20

CPC分类号： G06F8/3135

摘要： Unification of a disjunctive system is performed based on context identifiers within data structures that correspond to disjunctions. Each context identifier is a logical combination of choices, with each choice identifying one of the disjuncts of a disjunction in the system. Each choice can include a disjunction identifier and a choice identifier identifying one of the disjuncts of the identified disjunction. The logical combination of choices in a context identifier thus corresponds to a combination of disjuncts, all of which could be from different disjunctions. If two data units have context identifiers identifying contexts that are genuine alternatives, those data units are not unified. Data units that have context identifiers that are not genuine alternatives are unified. A set of context-value pairs, referred to as a disjunctive value, can be unified with another disjunctive value by considering all combinations of pairs of context identifiers that include one context identifier from each disjunctive value. The number of combinations of context identifiers in each disjunctive value is reduced by combining context-value pairs: Pairs with equal value tokens are combined by merging their context identifiers and unifying the value tokens. Pairs with f-structures as values are combined by merging context identifiers and unifying the f-structures. If it is necessary to insert a pointer, the pointer is inserted so that it initially leads to a disjunctive value, with the source of the pointer indicating which of the context-value pairs in the disjunctive value is to be accessed.

摘要翻译： 基于对应于分离的数据结构内的上下文标识符来执行分离系统的统一。 每个上下文标识符是选择的逻辑组合，每个选择标识系统中的一个分离的分离之一。 每个选择可以包括分离标识符和识别识别的分离的分离之一的选择标识符。 因此，上下文标识符中的选择的逻辑组合对应于分离的组合，所有这些都可以来自不同的分离。 如果两个数据单元具有识别作为真正替代品的上下文的上下文标识符，则这些数据单元不统一。 具有不是真正替代品的上下文标识符的数据单元是统一的。 称为分离值的一组上下文值对可以通过考虑从每个分离值包括一个上下文标识符的上下文标识符对的所有组合而与另一个分离值相统一。 通过组合上下文值对来减少每个分离值中的上下文标识符的组合数量：通过合并其上下文标识符并统一值令牌来组合具有相等值令牌的对。 具有f结构值的对通过合并上下文标识符和统一f结构来组合。 如果需要插入指针，则插入指针以使其最初导致分离值，指针的源指示要分离的值中的哪个上下文值对被访问。

公开(公告)号：US5625554A

公开(公告)日：1997-04-29

申请号：US916576

申请日：1992-07-20

申请人： Douglass R. Cutting ,  Per-Kristian G. Halvorsen ,  Ronald M. Kaplan ,  Lauri Karttunen ,  Martin Kay ,  Jan O. Pedersen

发明人： Douglass R. Cutting ,  Per-Kristian G. Halvorsen ,  Ronald M. Kaplan ,  Lauri Karttunen ,  Martin Kay ,  Jan O. Pedersen

IPC分类号： G06F17/30

CPC分类号： G06F17/30616 ,  G06F17/30663 ,  G06F17/30666 ,  G06F17/30672 ,  G06F17/30684 ,  G06F17/30985 ,  G06F17/30988 ,  Y10S707/99931

摘要： The present invention solves a number of problems in using stems (canonical indicators of word meanings) in full-text retrieval of natural language documents, and thus permits recall to be improved without sacrificing precision. It uses various arrangements of finite-state transducers to accurately encode a number of desirable ways of mapping back and forth between words and stems, taking into account both systematic aspects of a language's morphological rule system and also the word-by-word irregularities that also occur. The techniques described apply generally across the languages of the world and are not just limited to simple suffixing languages like English. Although the resulting transducers can have many states and transitions or arcs, they can be compacted by finite-state compression algorithms so that they can be used effectively in resource-limited applications. The invention contemplates the information retrieval system comprising the novel finite state transducer as a database and a processor for responding to user queries, for searching the database, and for outputting proper responses, if they exist, as well as the novel database used in such a system and methods for constructing the novel database.

公开(公告)号：US5564058A

公开(公告)日：1996-10-08

申请号：US450240

申请日：1995-05-25

申请人： Ronald M. Kaplan ,  Martin Kay

发明人： Ronald M. Kaplan ,  Martin Kay

IPC分类号： G06F17/30 ,  G06F9/00

CPC分类号： G06F17/30985 ,  Y10S707/99936

摘要： An FSM data structure is encoded by generating a transition unit of data corresponding to each transition which leads ultimately to a final state of the FSM. Information about the states is included in the transition units, so that the encoded data structure can be written without state units of data. The incoming transition units to a final state each contain an indication of finality. The incoming transition units to a state which has no outgoing transition units each contain a branch ending indication. The outgoing transition units of each state are ordered into a comparison sequence for comparison with a received element, and all but the last outgoing transition unit contain an alternative indication of a subsequent alternative outgoing transition. The indications are incorporated with the label of each transition unit into a single byte, and the remaining byte values are allocated among a number of pointer data units, some of which begin full length pointers and some of which begin pointer indexes to tables where pointers are entered. The pointers may be used where a state has a large number of incoming transitions or where the block of transition units depending from a state is broken down to speed access. The first outgoing transition unit of a state is positioned immediately after one of the incoming transitions so that it may be found without a pointer. Each alternative outgoing transition unit is stored immediately after the block beginning with the previous outgoing transition unit so that it may be found by proceeding through the transition units until the number of alternative bits and the number of branch ending bits balance.

摘要翻译： FSM数据结构通过产生对应于每个转换的数据的转移单元进行编码，这导致最终导致FSM的最终状态。 关于状态的信息被包括在转换单元中，使得编码的数据结构可以被写入而没有状态单元的数据。 到最终状态的进入转换单元都包含最终性的指示。 进入转移单元到没有输出转移单元的状态，每个都包含分支结束指示。 每个状态的输出转换单元被排序成比较序列，以便与接收到的元件进行比较，除了最后一个输出转换单元之外，除了最后一个输出转换单元之外的所有替代指示还包括随后的替代输出转换。 指示与每个转换单元的标签并入单个字节，并且其余字节值分配在多个指针数据单元中，其中一些指针数据单元开始全长指针，其中一些指针开始指向指针的表的指针索引 输入 指针可以用于状态具有大量进入转换的地方，或者来自状态的过渡单位块被分解以加速访问。 一个状态的第一个输出转换单元位于一个输入转换之后，从而可以在没有指针的情况下找到它。 每个替代的输出转换单元紧紧地存储在从先前的输出转换单元开始的块之后，以便可以通过进行转换单元找到直到替代位的数目和分支结束位的数目平衡为止。

公开(公告)号：US4738038A

公开(公告)日：1988-04-19

申请号：US5621

申请日：1987-01-21

申请人： Scott Tanne ,  Ronald M. Kaplan ,  George Wright, Sr.

发明人： Scott Tanne ,  Ronald M. Kaplan ,  George Wright, Sr.

IPC分类号： G09F15/00 ,  G09F23/06 ,  G09F3/18

CPC分类号： G09F23/06 ,  G09F15/0081

摘要： A lightweight compact, portable, advertising display apparatus provides an attractive, rotatable, miniature billboard assembly for displaying advertising material to viewing areas about the advertising display apparatus. The advertising display apparatus includes a plastic shaft with a convenient handle and a special coupling head which fits into corresponding keyholes in the container assembly to provide for easy assembly and disassembly of the unit when inserting and removing different advertising material.

摘要翻译： 轻巧紧凑的便携式广告显示装置提供了一种有吸引力的，可旋转的微型广告牌组件，用于向广告显示装置的观看区域显示广告材料。 广告显示装置包括具有便利手柄的塑料轴和装配在容器组件中的相应键孔中的特殊联接头，以便在插入和移除不同的广告材料时容易地组装和拆卸该单元。