CN111062832A

CN111062832A - Auxiliary analysis method and device for intelligently providing patent answer and debate opinions

Info

Publication number: CN111062832A
Application number: CN201911128217.XA
Authority: CN
Inventors: 沈木生
Original assignee: Individual
Current assignee: Individual
Priority date: 2019-11-18
Filing date: 2019-11-18
Publication date: 2020-04-24

Abstract

An auxiliary analysis method for intelligently providing patent answer suggestions comprises the following steps: acquiring a patent approval corresponding to the target patent application; performing matching search on the patent examination and positioning a target right item; and executing a first difference analysis process on each target right item and the comparison file matched with the target right item, wherein the first difference analysis process comprises the following steps: acquiring the content recorded by the target right item to form a first data set; acquiring identifications and quoted marks of N comparison files corresponding to the target rights; acquiring the quoted content of the N comparison files according to the identifications and the quoted marks of the N comparison files; forming the referenced contents of the N contrast files into a second data set; calculating a first similarity between the first and second data sets; determining a first difference level according to the first similarity and preset threshold information; and generating first answer proposal information corresponding to the target patent application according to the first difference level corresponding to each target right item. The invention can improve the efficiency, quality or success rate of patent answering operation.

Description

Auxiliary analysis method and device for intelligently providing patent answer and debate opinions

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to an analysis method and device for intelligently providing patent answer and debate opinions.

Background

During the patent application and examination, the patent applicant usually needs to reply to the notice of patent examination opinions issued by the patent office to overcome various problems existing in the new application documents of the patent. These problems include various types of defects and substantial defects in the patent new application. The most common substantial defect is that the patent application document may have a defect without inventiveness. And the answering work aiming at creativity is very strong in speciality, time-consuming and high in difficulty. Particularly, when receiving the examination advice notice related to the overall negative creativity, the patent applicant or the patent agent is required to spend a lot of time and effort on studying the examination advice notice, the comparison document and the patent application document, which is low in working efficiency, hard in labor and not necessarily high in success rate of answering and distinguishing.

In addition, as the creative work of patent answering in the prior industry adopts a pure manual work answering mode, is limited by the work experience and the service capability of different operators, the problem of uneven patent answering level may exist, and the quality of the patent answering work cannot be guaranteed.

Moreover, for patent engineers in enterprises, patent answer advice letters and patent answer manuscripts provided by patent agencies are generally required to be fully and manually reviewed, and relevant documents are re-read and analyzed, which also requires much reading and analyzing time, and thus a certain degree of workload and labor waste are caused.

Therefore, how to improve the efficiency, quality or success rate of patent answering work or reduce the load and strength of patent answering work becomes a technical problem to be solved urgently in the industry.

Disclosure of Invention

The embodiment of the invention provides an auxiliary analysis method and device for intelligently providing patent answer suggestions, so as to improve the patent answer efficiency, quality or success rate.

In a first aspect, an embodiment of the present invention provides an auxiliary analysis method for intelligently providing patent answer suggestions, including:

acquiring a patent examination opinion notice corresponding to a target patent application;

performing a matching search on the patent examination opinion notice to locate at least one target right; the target right item corresponds to a creative refusal clause and is matched with a comparison file;

executing first difference analysis processing on each target right item and a comparison file matched with the target right item; the first difference analysis process includes:

acquiring the content recorded by the target right item and forming a first data set;

acquiring identifiers of N comparison files corresponding to the target rights and respective quoted marks of the N comparison files from the examination opinion notice, wherein N is a positive integer; acquiring the quoted contents of the N comparison files corresponding to the target rights according to the identifications of the N comparison files and the quoted marks of the N comparison files respectively; forming the referenced contents of the N contrasts into a second data set of contrasts;

calculating a first similarity between the first data set of the target weight item and the second data set of the comparison file;

determining a first difference level between the first data set and the second data set according to the first similarity and preset threshold information;

and generating a first group of answer and debate advice information corresponding to the target patent application according to the first difference level respectively corresponding to each target right.

In a second aspect, an embodiment of the present invention provides an auxiliary analysis device for intelligently providing patent answer suggestions, including:

the acquisition module is used for acquiring a patent examination opinion notice corresponding to the target patent application;

the matching search module is used for executing matching search on the patent examination opinion notice and positioning at least one target right item; the target right item corresponds to a creative refusal clause and is matched with a comparison file;

the analysis processing module is used for executing first difference analysis processing on each target right item and the comparison file matched with the target right item; the first difference analysis process includes: acquiring the content recorded by the target right item and forming a first data set; acquiring identifiers of N comparison files corresponding to the target rights and respective quoted marks of the N comparison files from the examination opinion notice, wherein N is a positive integer; acquiring the quoted contents of the N comparison files corresponding to the target rights according to the identifications of the N comparison files and the quoted marks of the N comparison files respectively; forming the referenced contents of the N contrasts into a second data set of contrasts; calculating a first similarity between the first data set of the target weight item and the second data set of the comparison file; determining a first difference level between the first data set and the second data set according to the first similarity and preset threshold information;

and the answer and debate suggestion generation module is used for generating a first group of answer and debate suggestion information corresponding to the target patent application according to the first difference level corresponding to each target right item.

In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for intelligently providing an auxiliary analysis of patent answer suggestions.

In a fourth aspect, an embodiment of the present invention provides an electronic device, including:

one or more processors;

storage means for storing one or more programs;

when the one or more programs are executed by the one or more processors, the one or more programs cause the one or more processors to implement the method for intelligently providing assisted analysis of patent answer suggestions

The technical scheme has the following beneficial effects:

the patent answer advice notice, the comparison document and the application document are automatically analyzed by adopting a matching search technology, an information capture technology, a similarity analysis technology and an intelligent logic judgment technology, and the patent answer advice is quickly generated and output for a user to refer, so that a patent practitioner can be assisted, the patent answer operation time is saved, the substantive difference between the application and the comparison piece is quickly and accurately positioned and captured, the efficiency and the quality of the patent answer operation are improved, the patent applicant is helped to save answer cost and the examination program and the examination resources are saved. In addition, the embodiment adds a doubtful difference screening mechanism, and only automatically extracts or selects the associated content of the difference doubtful right item and the comparison file, and extracts and sends the corresponding comments on the creative doubtful right item in the review to the inventor or the enterprise patent engineer for rechecking, so that the method is beneficial to quickly gathering the doubtful difference points, saving precious time of the inventor, and avoiding the phenomenon that the inventor reads too many files to cause excessive burden and influence the completion of research and development tasks of the same job. In addition, the present embodiment adds a mechanism for predicting or prompting the success rate of answer, which is beneficial for the patent applicant to select the answer mode meeting the answer goal or expectation, and the patent applicant can make reasonable balance or compromise between the success rate of answer and the protection scope.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a flowchart of an auxiliary analysis method for intelligently providing patent answer suggestions according to embodiment 1 of the present invention;

FIG. 2 is a flowchart of another auxiliary analysis method for intelligently providing patent answer suggestions according to embodiment 2 of the present invention;

FIG. 3 is a partial flowchart of another auxiliary analysis method for intelligently providing patent answer suggestions according to embodiment 2 of the present invention;

FIG. 4 is a logic block diagram of an auxiliary analysis device for intelligently providing patent answer suggestions according to embodiment 3 of the present invention;

FIG. 5 is a logical block diagram of an electronic device of an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

At present, the patent answering work in the industry adopts a pure manual answering mode, and the mode has the problems of low patent answering efficiency, unstable answering quality, high answering work intensity and the like. In view of this, the embodiment of the present invention provides an auxiliary analysis system and method for intelligently providing patent answer opinions, which solves the pain in patent answer in the industry, quickly, accurately, comprehensively and intelligently provides answer reference opinions, and provides a referent answer direction or answer idea for patent operators to guide the answer operators to complete patent answer work with high efficiency or high quality.

Example 1

Fig. 1 is a flowchart of an auxiliary analysis method for intelligently providing patent answer suggestions according to embodiment 1 of the present invention. As shown in fig. 1, the method comprises the steps of:

step S110: and acquiring a patent examination opinion notice corresponding to the target patent application.

The step may specifically include: receiving a patent examination opinion notice in an electronic format uploaded by a user; or, receiving a patent examination opinion notice in electronic format sent by a user through an instant messaging tool of the mobile communication terminal; or, receiving the patent examination opinion notice in electronic format, which is scanned and input by the user through a scanning tool (such as a scanner) to the patent examination opinion notice in paper format; or, receiving all pictures of patent examination suggestion notice taken by the user through a camera built in the mobile communication terminal; or remotely downloading the patent examination opinion notice in an electronic format in an open state from a website of the national intellectual property office (such as a Chinese and multi-national patent examination information inquiry website) or other patent databases. The patent examination comment notice in the form of a picture or PDF can be converted into an editable text format by means of an OCR (Optical character recognition) tool or software.

Step S120: performing matching search on the patent examination opinion notice to locate a target right item; the target rights correspond to the inventive rejectional terms and are matched with the comparison document.

In this step, a matching search may be performed on the patent examination opinion notice in various ways to locate the target rights. As an example, matching search can be implemented through a web crawler tool or a regular expression, and the target weight is located. A web crawler is a program or script that can automatically capture information according to rules. Web crawlers can be broadly classified into the following types according to system structure and implementation technology: general Purpose Web crawlers (General Purpose Web Crawler), Focused Web Crawler (Focused Web Crawler), Incremental Web Crawler (Incremental Web Crawler), Deep Web Crawler (Deep Web Crawler). The focused web crawler is a web crawler program oriented to specific needs, and is different from a general web crawler in that: the focused web crawler screens and processes the content when implementing web page or data capture, and only web page or data information related to the requirement is captured as much as possible, so that hardware and network resources are greatly saved. The crawler may be made using the java or python programming languages. In one example, regular expressions can be used or embedded in a web crawler to obtain relevant content needed in the present embodiment. If a right does not relate to a creative refund term, it is not considered a target right. If a right item relates to a creative refusal clause, but the unexamined opinion notice allocates a corresponding comparison file, the right item is temporarily not taken as a target right item. The target claim may be an independent claim or a dependent claim. The objective right may be that the whole content is disclosed by each comparative document or equivalently, or that only part of the content is disclosed by the comparative documents, and the content of the rest part of the right is evaluated as belonging to the common general knowledge, the conventional technical means, or the similar words such as the conventional technology, the conventional selection, the conventional design, the conventional process, the conventional selection, the conventional structure, the conventional mode and the like.

Step S130: executing first difference analysis processing on each target right item and a comparison file matched with the target right item; the first difference analysis process includes the steps of:

step S131: the content of the target rights is obtained and a first data set is formed.

In this step, all or part of the content recorded by the target weight item may be obtained through a web crawler tool or a regular expression, and a first data set is formed. The partial content may be the content described as the distinguishing technical feature in the target right item, or the partial content may be the content associated with only the comparison file in the distinguishing technical feature of the target right item, that is, in this case, the distinguishing technical feature of the target right item is divided into two parts, one part of the examined opinion notice is configured with the corresponding comparison file, and the other part of the examined opinion notice is not evaluated by referring to the corresponding comparison file. As an alternative, an input box may be provided on a computer software Interface, a mobile APP program, or a GUI (Graphical User Interface) of a web page for receiving User-input (e.g., pasted) content of the target rights entry. As yet another alternative, an information upload box may be provided for receiving the content of the target rights item uploaded by the user.

Step S132: acquiring the identifications of N comparison files corresponding to the target right item and the respective quoted marks of the N comparison files from the review comment notice; wherein N is a positive integer. And acquiring the quoted contents of the N comparison files corresponding to the target rights according to the identifications of the N comparison files and the quoted marks of the N comparison files respectively. The referenced contents of the N contrast files are formed into a second data set of contrast files.

In this step, the identifier of the comparison document may be the publication number or name of the comparison document, and the reference mark of the comparison document refers to at least one of the number of pages, number of columns, number of paragraphs, number of lines, and number of volumes that are referred to in the comparison document to evaluate the current target patent application.

In this step, when the comparison documents are patent documents, the cited contents of the N comparison documents corresponding to the target rights can be obtained from the patent database server through the internet by means of a web crawler and/or a regular expression matching method according to the identifiers of the N comparison documents and the respective cited marks of the N comparison documents. When the reference document is a non-patent document, such as a paper, a periodical, a magazine, or a book, it is usually issued together with the examination as an attachment to the examination, so that OCR can be performed to perform character recognition to extract the corresponding cited content. And when the foreign language comparison files exist in the N comparison files, acquiring the Chinese translation of the cited content of the foreign language comparison files from the patent database or the translation platform through a web crawler.

In this step, the referenced contents of the N comparison files are sequentially arranged according to the sequence of the numbers of the comparison files to form a second data set.

Step S133: a first similarity between the first data set of the target rights item and the second data set of the comparison file is calculated.

In this step, the similarity may be calculated from one or more text similarity algorithm combinations of cosine similarity (cosine similarity), Dice coefficient, Longest Common substring (Longest Common substring), Longest Common Subsequence (Longest Common Subsequence), simple Common word, Edit Distance (Edit Distance), Hamming Distance (Hamming Distance), jackard similarity coefficient (Jaccard index), Euclidean Distance (Euclidean Distance), manhattan Distance (manhattan Distance).

Cosine similarity is to evaluate the similarity of two vectors by calculating the cosine value of the included angle between the two vectors. The cosine of the included angle has the value range of [ -1,1 ]. The larger the cosine of the included angle is, the smaller the included angle between the two vectors is, and the smaller the cosine of the included angle is, the larger the included angle between the two vectors is. When the directions of the two vectors are coincident, the cosine of the included angle takes the maximum value of 1, and when the directions of the two vectors are completely opposite, the cosine of the included angle takes the minimum value of-1.

The Dice coefficient may calculate the similarity of two strings:

Dice(s1,s2)＝2*comm(s1,s2)/(leng(s1)+leng(s2))。

here, comm (s1, s2) is the number of the same character in s1, s2, and leng (s1), leng (s2) is the length of the character strings s1, s 2.

The difference between the Longest Common Substring (changecommon Substring) and the Longest Common subsequence (changecommon substsequence): the longest common substring algorithm requires continuity in the original string, while the longest common subsequence algorithm only needs to keep consistent relative order and does not require continuity. For example, X ═ { a, Q,1,1 }; y ═ a,1,1, d, f, then { a,1,1} is the longest common subsequence of X and Y, but not their longest common string. This type of method adds a requirement that the character sequence, i.e. the character composition and character sequence are the same, is similar to the character string.

Simple common words refer to evaluating the similarity of words common to two documents by calculating their total number of characters divided by the number of characters of the longest document.

The Edit Distance (Edit Distance), also called Levenshtein Distance, refers to the minimum number of editing operations required to change one string into another string. Permitted editing operations include replacing one character with another, inserting one character, and deleting one character. Generally, the smaller the edit distance, the greater the similarity between two strings. Calculating a similarity formula: 1- (their edit distance ÷ maximum of two string lengths).

Hamming distance (Hamming distance), the Hamming distance between two equal-length character strings is the number of different characters at the corresponding positions of the two character strings. In other words, it is the number of characters that need to be replaced to convert one string into another.

Jaccard similarity coefficient, a probability used to compare similarity and dispersion in a sample set, is equal to the ratio of the sample set intersection to the sample set, i.e., J ═ a ∩ B | ÷ | a ∪ B |, where A, B represents both sample sets.

Euclidean distance, a commonly used definition of distance, refers to the true distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). The similarity is obtained by 1 ÷ (1+ euclidean distance).

Manhattan distance, which refers to the distance between two points in the north-south direction plus the distance in the east-west direction, i.e., d (i, j) ═ xi-xj | + | yi-yj |. The similarity is obtained by 1 ÷ (1+ manhattan distance).

The distance and the text similarity score are in an inverse proportion relation, the farther the distance is, the less similar the distance is, the distance tends to be infinite, the text similarity score tends to be 0, and the text similarity score tends to be 1 or equal to 0.

In some embodiments, the first similarity between the first data set of the target rights and the second data set of the comparison file may also be calculated using an Elasticsearch. The ElasticSearch is a Lucene-based search server. The full-text search engine with distributed multi-user capability is provided, and is based on RESTful (RESTful is the specification, constraint and principle of an architecture, and the architecture conforming to the specification is the RESTful architecture, which is Representational state transfer) web interface. The Elasticsearch was developed in Java and published as an open source under the license terms of Apache (a Web server side software), and is currently a popular enterprise-level search engine. In this embodiment, the first similarity is calculated by using a self-contained similarity calculation method in the elastic search. The elastic search bottom layer employs Lucene (a full-text search engine), and the Lucene score calculation integrates Boolean model (Boolean model), TF-IDF (Term Frequency-Inverse Document Frequency), and vector space model.

In this step, the first similarity between the first data set of the target weight and the second data set of the comparison file may include a similarity based on a superior-inferior relationship and a synonymous relationship.

Step S134: a first difference level between the first data set and the second data set is determined according to the first similarity and preset threshold information.

In this step, the preset threshold information may include a plurality of thresholds, that is, the similarity is divided into a plurality of sections from 0 to 1, and each section corresponds to one difference level. See table 1 for an example below:

table 1: similarity and difference level correspondence table 1

Step S140: and generating a first group of answer suggestion information corresponding to the target patent application according to the first difference level corresponding to each target right item.

Referring to fig. 3, the step S140 may specifically include the following steps:

(1) generating a first answer indication whether to initiate an answer

After determining that there is a moderate difference or a high difference in the level of difference corresponding to the at least one target right, generating a first answer indication configured to: indicating that the target patent application has a patent authorization prospect, and proposing to continue patent answering operation; otherwise, the first answer indication is configured to: instructing to abandon patent answering work.

(2) Generating a second answer indication of whether to modify an individual right item in an answer

After determining that the difference level corresponding to the independent claim is a height difference or a degree difference, generating a second answer indication configured to: indicating that the independent claims are not to be amended; otherwise, the second answer indication is configured to: indicating that the independent claim needs to be amended.

(3) Third answer indication for generating whether a target right item can be used as basis for amending an independent claim

Upon determining that there is at least one subordinate target weight for which the level of difference is a medium difference or a high difference, then generating a third answer indication configured to: instructing to add the one or more dependencies to the independent claim or to rewrite the one or more dependencies to the independent claim; or filed as a divisional application with one or more dependent claims; otherwise, the third answer indication is configured to: indicating that the dependent claim is not inventive or that it alone may not be the basis for modifying the independent claim.

(4) Generating a fourth answer indication of whether the target weight requires initiation of manual review

After determining that there is a difference level corresponding to one target right that is a high difference or a light difference, generating a fourth answer indication configured to: indicating not to carry out manual recheck; otherwise, the fourth answer indication is configured to: and instructing manual review of the target right, and further, associatively recording and outputting text contents of the target right required to be manually reviewed and corresponding referenced contents of the contrast piece, as well as similarity values between the text contents and the referenced contents, for analysis by a patent operator.

(5) Generating a fifth answer indication representing answer prediction success rate corresponding to the target weight item

After determining that there is a moderate difference in the level of difference corresponding to any of the target rights, generating a fifth answer indication configured to: the target weight item is used as a basis for modifying the independent right, and the predicted answer discrimination success rate is medium.

After determining that there is a difference level corresponding to any one of the target rights as a height difference, generating a fifth answer indication configured to: the target weight item is used as a basis for modifying the independent right, and the predicted answer discrimination success rate is higher.

Table 2: similarity and difference level correspondence table 2

Target rights item	Comparison document	Similarity value	Interval of similarity	Level of difference
					Weight 1	D1+D2	85％	【0.8，1】	Slight difference
Right 2	D1	75％	【0.5，0.8)	Moderate difference
					Weight 3	D1+D3	90％	【0.8，1】	Slight difference
Claim 4	D3	45％	【0，0.5)	Height difference
					Right 5	D2+D3	95％	【0.8，1】	Slight difference

As an alternative, in table 2 and tables described later, information in the column of "similarity degree section" may be omitted or hidden. In table 2 and tables described later, two columns of information, "similarity value" and "difference level" may be displayed alternatively. In table 2 and the tables described below, the information displayed in the form of a table is not necessary, and those skilled in the art can replace the table with a mind map or any other suitable display mode.

As an example, the corresponding answer suggestion table 3 may be automatically generated according to the examples and computer programs in Table 2.

Table 3: first answer advice list

The auxiliary analysis method for intelligently providing patent answer suggestions has the following beneficial technical effects:

the patent answer advice notice, the comparison document and the application document are automatically analyzed by adopting a matching search technology, an information capture technology, a similarity analysis technology and an intelligent logic judgment technology, and the patent answer advice is quickly generated and output for a user to refer, so that a patent practitioner can be assisted, the patent answer operation time is saved, the substantive difference between the application and the comparison piece is quickly and accurately positioned and captured, the efficiency and the quality of the patent answer operation are improved, the patent applicant is helped to save answer cost and the examination program and the examination resources are saved. In addition, the embodiment adds a doubtful difference screening mechanism, and only automatically extracts or selects the associated content of the difference doubtful right item and the comparison file, and extracts and sends the corresponding comments on the creative doubtful right item in the review to the inventor or the enterprise patent engineer for rechecking, so that the method is beneficial to quickly gathering the doubtful difference points, saving precious time of the inventor, and avoiding the phenomenon that the inventor reads too many files to cause excessive burden and influence the completion of research and development tasks of the same job. In addition, the present embodiment adds a mechanism for predicting or prompting the success rate of answer, which is beneficial for the patent applicant to select the answer mode meeting the answer goal or expectation, and the patent applicant can make reasonable balance or compromise between the success rate of answer and the protection scope. In addition, the method of the present embodiment may be used for training bands for assistant patent engineers or assistant patent agents. In addition, the method of the embodiment can be used for realizing quick and concise preview of the patent examination opinion notice, so that simplified presentation or concise display of multi-dimensional analysis results of patent examination and comparison files with longer length can be realized in a mobile office scene, and a patent operator can quickly obtain examination evaluation ideas and veins of examination and comparison files and associated contents of the comparison files in the break-away time of commuting or business travel, so as to consider answer strategies in advance and quickly position a dispute focus or a potential answer breakthrough point according to the analysis suggestions of an artificial intelligent analysis tool, thereby improving the working efficiency and quality of fragmentation time.

Example 2

Fig. 2 is a flowchart of another auxiliary analysis method for intelligently providing patent answer suggestions according to embodiment 2 of the present invention. As shown in fig. 2, on the basis of fig. 1, the method further includes the following steps:

step S210: and executing second difference analysis processing on each target right item and the comparison file matched with the target right item. The second difference analysis process may specifically include the steps of:

step S211: the content of the target rights is obtained and a first data set is formed.

Step S212: segmenting the first data set of target rights into a plurality of first-type strings, the segmenter between adjacent strings comprising: line breaks, paragraph separators, or other specific punctuation marks (e.g., comma, pause, or semicolon), where comma has a higher priority than pause to avoid over-fine segmentation resulting in incomplete semantics. Preferably, each first-type character string is divided into a corresponding technical feature, and the technical feature may be, for example, a processing step in a method right item, or a sub-processing step, and the processing step or the sub-processing step includes at least a verb. In step(s), the target weight item can be divided into multiple natural segments, multiple lines or multiple phrases by various existing means. For example, three ways of segmenting a string in python may be used, including: split () is used for splitting, and a character list of a split part is returned after splitting; split () of re module is used to split character string, and returned after splitting is character list of split part, so as to realize one-time splitting of multiple split characters; the character string segmentation is realized by using a character string function partition (namely str.partition ()) or rpartion (namely str.rpartion ()), wherein both functions receive a segmentation character string as a parameter, segment a target character string into two parts and return a ternary tuple (head, sep, tail) containing a segmentation character.

Step S213: and performing stop word filtering processing on each first-type character string, wherein stop words comprise conventional stop words and customized stop words, and a plurality of second-type character strings which are subjected to stop word filtering processing and correspond to the target rights are obtained. Stop Words (Stop Words) refer to the fact that in information retrieval, some characters or Words are automatically filtered before or after processing natural language data (or text) in order to save storage space and improve search efficiency. Customized stop words include, but are not limited to: "characterized in," "wherein," "said," "comprising," and the like. Customized stop words may also include words of ordinary skill in the art having a general meaning, such as "CPU," "processor," "unit," "module," and the like.

Step S214: and acquiring the identifications of the N comparison files corresponding to the target right item and the respective quoted marks of the N comparison files from the examination opinion notice, wherein N is a positive integer. And acquiring the quoted content of the N comparison files corresponding to the target rights according to the identifications of the N comparison files and the quoted marks of the N comparison files respectively. The referenced contents of the N contrast files are formed into a second data set of contrast files.

Step S215: and performing matching search in the second data set of the comparison file, and determining at least one text content paired with each second-type character string of the target right item. In this step, each second-type character string includes one or more keywords, the one or more keywords and synonyms or expansion words or hyponyms thereof are extracted through a preset synonym library or wikipedia, matching search is performed in a second data set of the comparison file, so that all sentences or paragraphs containing the one or more keywords, synonyms or expansion words are found in the second data set, and the sentences or paragraphs belong to paired text contents to be further analyzed.

Step S216: and calculating and obtaining a second similarity between each second-class character string of the target right item and the paired text content in the second data set of the comparison file according to each second-class character string of the target right item and at least one paired text content. In the step, a plurality of second similarity degrees can be formed through calculation, then the second similarity degrees are arranged in a descending order, and a set number of high-association matching texts with the similarity degrees in the front order are extracted; then, the highest similarity value or the weighted average similarity value between the high-association matching texts and the second type of character strings is used as the second similarity between the second type of character strings and the paired text contents in the second data set of the comparison file.

Step S217: and determining a second difference level between each second-type character string in the target weight item and the second data set of the comparison file according to the second similarity and preset threshold information.

Step S220: and generating second answer proposal information corresponding to the target patent application according to the second difference level respectively corresponding to each second type character string of each target right item.

This step S220 may specifically include:

(1) generating a sixth answer indication for locating a height difference technical feature

When the second difference level corresponding to one technical feature character string is determined to be a height difference, and the first difference level corresponding to the target right to which the technical feature character belongs is determined to be a middle difference, generating a sixth answer indication, wherein the sixth answer indication is configured to: instructing to add the technical feature character string or a target right item to which it belongs to an independent right item and stating in an opinion statement that the technical feature character string is not disclosed by each comparison document; when the technical feature string has been described in an independent claim, an indication is generated to perform patent answering without modifying the independent claim.

(2) Seventh answer indication whether generating technical characteristic string requires triggering manual review

When the second difference level corresponding to one technical characteristic character string is determined to be moderate difference, and the first difference level corresponding to the target right to which the technical characteristic character belongs is determined to be light difference, generating a seventh answer indication, wherein the seventh answer indication is configured to: and the technical characteristic character string is recorded and output in association with the corresponding matched text content and the difference level thereof so as to trigger the starting of manual review.

Based on tables 2 to 3, after performing the second difference analysis processing, a second answer advice information as shown in table 4 may be generated, based on the same example.

Table 4: example list after combination of first and second set of answer suggestions

In a further embodiment, after obtaining a plurality of second-class character strings subjected to stop word filtering processing and corresponding to the target weight items in step S213, the method further includes the following steps: and extracting a plurality of feature words from each second-class character string, for example, performing word segmentation processing on each second-class character string to obtain a plurality of feature words. Alternatively, a plurality of feature words are extracted from each second-type character string by semantic analysis, or a plurality of feature words are extracted from each second-type character string by a Term Frequency-Inverse document Frequency (TF-IDF) method.

After the step S216 calculates a plurality of second similarities between each of the second-type character strings in the target weight and the paired text contents, the method further includes the following steps: calculating a plurality of third similarities between each feature word included in each second-type character string of the target weight item and similar words in a plurality of paired text contents; outputting similar words with similarity higher than a set threshold and corresponding third similarity; generating a third difference level aiming at each feature word of each second type character string in the target weight item according to the third similarity and preset threshold information;

and generating a third group of answer and debate suggestion information corresponding to the target patent application according to the third difference level corresponding to each feature word.

Wherein, according to the third difference level corresponding to each feature word, generating a third group of answer suggestion information corresponding to the target patent application may specifically include:

(1) when it is determined that the third difference level corresponding to any feature word is a height difference, generating an eighth answer indication, where the eighth answer indication is configured to: the characteristic word is highlighted and identified as a preferred answer break point, and the characteristic word can be discussed around the characteristic word as a modification basis or in a meaning statement book.

(2) Generating a ninth answer indication when the third difference level corresponding to any feature word is determined to be a moderate difference, the ninth answer indication being configured to: and highlighting the characteristic word and the associated similar word and the third difference level, and identifying the characteristic word as a potential answer and debate breakthrough point, wherein the characteristic word can be discussed around the characteristic word as a modification basis or in a comment book after manual review.

In a further embodiment, the method may further comprise the steps of: capturing all or specified technical effect descriptions from the target patent application to form a first technical effect set; capturing all or appointed technical effect descriptions from all comparison files corresponding to the target patent application to form a second technical effect set; calculating a fourth similarity of the first technical effect set and the second technical effect set; generating a fourth difference level between the target patent application and all comparison files according to the fourth similarity and preset threshold information; and generating a fourth group of answer and debate advice information corresponding to the target patent application according to the fourth difference level. The specified technical effect description means a technical effect description only recited in the summary of the invention in the specification.

When it is determined that the fourth level of difference is a height difference, the fourth set of answer advice information is generated as a tenth answer indication: which indicates that the differences in technical effect are discussed in the statement of opinions.

When it is determined that the fourth level of difference is a medium difference, generating a fourth set of answer advice information as an eleventh answer indication: it indicates that the difference of technical effects is questionable and needs to be manually rechecked; and, the first technical effect set and the second technical effect set are recorded and output in correspondence.

When it is determined that the fourth level of difference is a light difference, the fourth set of answer advice information is generated as a twelfth answer indication: which indicates that no answer can be made from the technical effect dimension or that no statement can be made on the reason that the target patent application achieves the unexpected advantageous technical effect.

In a further embodiment, the method may further comprise the steps of: capturing all or specified technical problem descriptions from the target patent application to form a first technical problem set; capturing all or appointed technical problem descriptions from all comparison files corresponding to the target patent application to form a second technical problem set; calculating a fifth similarity of the first technical problem set and the second technical problem set; generating a fifth difference level between the target patent application and all comparison files according to the fifth similarity and preset threshold information; and generating a fifth group of answer and suggestion information corresponding to the target patent application according to the fifth difference level. The specified technical problem description is the technical problem description only described in the summary of the invention in the specification.

When it is determined that the fifth level of difference is a height difference, generating a fifth set of answer advice information as a thirteenth answer indication: which indicates that differences in technical issues are discussed in the opinion statement.

When it is determined that the fifth level of difference is moderate, generating the fifth set of answer advice information as a fourteenth answer indication: it indicates that the difference of technical problems is questionable and needs to be manually rechecked; then, the first technical problem set and the second technical problem set are recorded and output in a corresponding manner.

When it is determined that the fifth level of difference is a light difference, the fifth answer advice information is generated as a fifteenth answer indication: indicating that no answer can be made from the technical issue dimension, or that the review opinions can not reason about the technical issue being incorrectly recognized, or that the opinions can not be made because there is no technical hint of binding between the comparison documents.

In this embodiment, obtaining the first data set of the target right, obtaining the identifiers of the N comparison files corresponding to the target right, obtaining the respective quoted marks of the N comparison files, and obtaining the quoted contents of the N comparison files corresponding to the target right are implemented by using a web crawler tool or a regular expression matching algorithm.

In a further embodiment, the method further comprises: judging whether the examination opinion notice can be matched with and searched for a second target right item, wherein the second target right item contains the right item of a preset examination keyword and does not have a matched comparison file; the preset examination keyword includes at least one of: a first type of examination keyword, which is used for representing that the content claimed by the current claims belongs to common general knowledge; the second category of examination keywords is used for characterizing the claimed content of the current claims as belonging to conventional technical means, conventional techniques, conventional choices, conventional designs, conventional processes, conventional choices, conventional structures, conventional manners, and the like.

When the second target weight is searched for by matching, the similarity value of the second target weight is set to zero, which is equivalent to a sixth difference level of 100%, and a sixth set of answer suggestions is generated. The sixth set of answer suggestions is generated as at least one answer indication as follows: a sixteenth answer indication that indicates that the second target right can be selected to be added to the independent right to overcome the creative problem of the independent right; the technical problem corresponding to the second target right item and the obtained technical effect are discussed in the opinion statement; and/or, it may be indicated that the request for the examiner to provide proof that the second objective right is in the common general knowledge, common technical means, or common technical means in the opinion statement.

The following are exemplified:

table 5: example form comprising a sixth set of answer suggestions

As shown in table 5, a list of information indicators, namely "evaluation reason/review keyword", is further added in table 5, and then the calculated similarity value is combined to comprehensively implement quick preview of the abstract or key information of the review, and display subjective evaluation words in the review and evaluation process, which is beneficial for patent operators to quickly grasp review thought or pulse, and quickly query the review of the current patent by using the mobile phone APP at fragmented time to preliminarily determine the direction of answering and debarking. In an application scenario where simplified display is required, for example, in an APP display interface of a mobile phone, columns or fields of "technical features" and "associated texts" in the above table may be omitted, or simplified display may be performed, for example, only a limited number of characters at the beginning, middle, or end of each character is displayed, or folding display is performed, and when a user clicks, the complete information content is displayed.

In some other embodiments, the generating of the seventeenth answer indication for the sixth set of answer suggestions includes: according to a crawler algorithm and/or a regular expression matching algorithm, matching search is carried out on the characteristic part content (removing redundant information, such as ' the ' and other conventional stop words ') of a second target right or a keyword contained in the second target right in the specification of the target patent application, whether a technical effect description associated with the second target right is matched or not is judged, when the second target right is determined to have a corresponding technical effect description in the specification, an indication that the second target right is recommended to be used as a conclusion is generated, and when the second target right is determined not to have a corresponding technical effect description in the specification (such as the invention content and the specific embodiment) of the target patent application, an indication that the second target right is not creative and cannot be used as a conclusion is generated. The above-mentioned answering breakthrough point means that the second target right can be used alone or in combination with the right cited therein as the basis for modifying the exclusive right, and the reason for answering can be stated in the statement of opinions around the second target right, the technical problem solved thereby and the technical effect achieved thereby. The above-mentioned determination of whether to match the technical effect description associated with the second target right may be implemented in various ways. For example, when a keyword or similar word contained in the second target weight item is matched in the specification, a sentence or a paragraph containing the keyword or similar word is extracted (for example, a semantic segment with a preset character length can be cut forward and/or backward from the matched and located keyword or similar word by a center according to a preset cutting algorithm rule), then a keyword (for example, beneficial effect, advantage, benefit, technical effect, and the like) for representing a technical effect is searched in the extracted sentence or paragraph, when the keyword for representing the technical effect is searched, it is determined that a technical effect description associated with the second target weight item is matched in the specification, and then the technical effect description associated with the second target weight item can be further output.

In other embodiments, the method further comprises the step of generating a seventh set of answer suggestions for indicating the content of the differences between the claims and the specification of the present target patent application, comprising the steps of:

extracting all keywords from the claims of the target patent application to form a first keyword set; for example, the following unsupervised keyword extraction algorithm may be employed: TF-IDF algorithm, TextRank algorithm and topic model algorithm (including LSA (Latent Semantic Analysis), LSI (Latent Semantic Indexing), LDA (Latent Dirichlet Allocation). The TextRank algorithm is a graph-based ranking algorithm for text. The method comprises the steps of dividing a text into a plurality of composition units (words and sentences), establishing a graph model, sequencing important components in the text by using a voting mechanism, and extracting keywords only by using the information of a single document. In the specific embodiment of the present specification of the subject patent application, all keywords are extracted in part to form a second set of keywords. The first set of keywords and the second set of keywords are compared. Generating a third keyword set which comprises all the keywords which are only recorded in the second keyword set but not recorded in the first keyword set, namely obtaining a difference set according to the sum set and the intersection set by solving the sum set and the intersection set. For example, the difference, identity (difference, intersection, union) between two arrays can be compared using the pythoset () function. Then, the third set of keywords is output. Finally, a seventh set of resolution suggestions is generated based on the third set of keywords representing the content of the differences between the claims and the description of the present target patent application. The seventh set of answer suggestions includes an eighteenth answer indication: when the third keyword set is determined to be an empty set, generating an indication that substantial differences cannot be found from the specification so as to modify the independent claim to overcome the creative problem thereof. And when the third keyword set is determined to be a non-empty set, outputting the third keyword set to a display module for patent operators to verify, and generating an indication that the independent right item can be modified according to the third keyword set so as to prompt the patent operators to select technical features meeting conditions from the third keyword set to modify the independent right item. Further, when the third keyword set is determined to be a non-empty set, a Jaccard similarity coefficient is calculated, wherein the Jaccard similarity coefficient is equal to the ratio of the third keyword set to the union formed by the first keyword set and the second keyword set. A seventh difference level is obtained from the Jaccard similarity coefficient.

Table 6: the answer report of this embodiment includes various groups of answer suggestions and a schematic list of answer instructions

As shown in Table 6, as an example, sets of answer suggestions that may be included in the generated answer analysis report, the answer indication included in each set of answer suggestions, and the primary function of the answer indication are listed in some embodiments. For the sake of brevity, the above-mentioned tables only briefly express the brief introduction of each answer indicating the main function, but do not limit the embodiment.

In an alternative embodiment, the method further comprises the steps of:

acquiring user answering target information input by a user or configured in advance, wherein the user answering target information comprises: first answer target information indicating that the patent application is expected to obtain the fastest authorization; second answer target information indicating that the patent application desires to obtain the maximum protection scope; third answer target information indicating that the patent application desires a balance between granted speed and protection scope;

generating first answer suggestion information corresponding to the target patent application according to the first difference level corresponding to each target right item respectively, comprising: when the first answer target information is acquired, generating an indication that a plurality of subordinate rights items with first difference levels of moderate differences or high differences are added to the independent rights items; when the second answer target information is acquired, generating an indication that the independent right item is not modified; when the third answer target information is acquired, an indication is generated that only one subordinate right item having the first difference level of the height difference is added to the independent right item. Wherein the priority generates an indication that a subordinate item that directly references the independent item and has a first difference level of height difference is added to the independent item. When there are a plurality of subordinate items satisfying the above condition, an instruction to preferentially add the top-ranked subordinate item to the independent item is generated.

In some embodiments, the new answer suggestions are obtained from any combination of the above-described sets of answer suggestions or levels of difference.

For example: when the method judges whether the independent right item is modified, according to the technical characteristic difference level (at least one of a first difference level, a second difference level or a third difference level) corresponding to the independent right item, the technical problem difference level (a fifth difference level) and the technical effect difference level (a fourth difference level), the preset weights of all parts are combined to obtain the overall difference level between the independent right item and all comparison file sets, and whether the independent right item is modified is determined according to the overall difference level.

For example: when the method judges how many modification modes of the independent rights are available, according to the technical feature difference level (at least one of the first difference level, the second difference level or the third difference level) corresponding to each subordinate right, whether the right (the sixth difference level) contains the preset examination keyword and does not have the matched comparison file, and the difference content or the difference level (the seventh difference level) between the claims and the specification of the target patent application, a plurality of modification modes of modifying the independent rights are generated.

In the present embodiment, the above-mentioned patent answer advice information is output by at least one of: outputting the generated preliminary patent answer advice information in a form of a webpage in a website; and/or outputting the generated preliminary patent answer advice information in the form of a display interface of a built-in APP (application) program or WeChat applet of the mobile communication terminal; and/or outputting the generated preliminary patent answer advice information in the form of a display interface of a client software program running on a computer; and/or outputting the generated preliminary patent answer advice information in a voice or video mode.

The auxiliary analysis method for intelligently providing patent answer and debate suggestions in embodiment 2 of the invention is beneficial to the answer and debate examination of patent workers by analyzing the similarity between each technical characteristic character string in the right item and the corresponding content in the comparison file set and providing corresponding matching content, and in addition, the answer and debate suggestions aiming at each technical characteristic are automatically output, the analysis granularity is higher, the difference between the application and the comparison file is favorably and accurately positioned, and the accurate answer and high-efficiency answer and debate analysis is realized. The method of the embodiment can generate at least seven groups of 18 answer instructions for the patent operator to refer to, comprehensively analyze various differences and difference degrees of the application and the comparison document from multiple different dimensions, and provide corresponding analysis suggestions, thereby improving the quality and efficiency of the patent answer.

Example 3

Fig. 4 is a logic block diagram of an auxiliary analysis device for intelligently providing patent answer suggestions provided in embodiment 3, as shown in fig. 4, which includes:

and the answer and debate suggestion generation module is used for generating first answer and debate suggestion information corresponding to the target patent application according to the first difference level corresponding to each target right item.

An embodiment of the present invention further provides an electronic device, as shown in fig. 5, including one or more processors 301, a communication interface 302, a memory 303, and a communication bus 304, where the processors 301, the communication interface 302, and the memory 303 complete communication with each other through the communication bus 304.

A memory 303 for storing a computer program;

the processor 301, when executing the program stored in the memory 303, implements the steps of the auxiliary analysis method for intelligently providing patent answer suggestions.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the electronic equipment and other equipment.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.

The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when being executed by a processor, the computer program realizes the steps of the intelligent auxiliary analysis method for providing patent answer advice.

Those of skill in the art will further appreciate that the various illustrative logical blocks, units, and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, elements, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present embodiments.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. For example, a storage medium may be coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may be located in a user terminal. In the alternative, the processor and the storage medium may reside in different components in a user terminal.

In one or more exemplary designs, the functions described above in connection with the embodiments of the invention may be implemented in hardware, software, firmware, or any combination of the three. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media that facilitate transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a general purpose or special purpose computer. For example, such computer-readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store program code in the form of instructions or data structures and which can be read by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Additionally, any connection is properly termed a computer-readable medium, and, thus, is included if the software is transmitted from a website, server, or other remote source via a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wirelessly, e.g., infrared, radio, and microwave. Such discs (disk) and disks (disc) include compact disks, laser disks, optical disks, DVDs, floppy disks and blu-ray disks where disks usually reproduce data magnetically, while disks usually reproduce data optically with lasers. Combinations of the above may also be included in the computer-readable medium.

The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. An auxiliary analysis method for intelligently providing patent answer suggestions is characterized by comprising the following steps:

2. The method of claim 1, further comprising:

executing second difference analysis processing on each target right item and the comparison file matched with the target right item; the second difference analysis process includes:

segmenting the first data set of target rights into a plurality of first-class character strings;

performing stop word filtering processing on each first type of character string, wherein stop words comprise conventional stop words and customized stop words, and a plurality of second type of character strings which are subjected to stop word filtering processing and correspond to the target weight item are obtained;

performing matching search in a second data set of the comparison file, and determining at least one text content paired with each second-type character string of the target right item;

calculating at least one second similarity between each second-type character string of the target right item and at least one paired text content;

determining a second difference level between each second-type character string in the target weight item and a second data set of the comparison file according to the at least one second similarity and preset threshold information;

and generating a second group of answer and debate suggestion information corresponding to the target patent application according to the second difference level respectively corresponding to each second type character string of each target right item.

3. The method according to claim 2, further comprising, after obtaining the stop word filtering processed plurality of second-class character strings corresponding to the target rights item:

extracting a plurality of feature words from each second-type character string;

after calculating a plurality of second similarities between each second-type character string in the target right item and the paired text contents, the method further comprises:

calculating a plurality of third similarities between each feature word included in each second-type character string of the target weight item and similar words in a plurality of paired text contents;

outputting similar words with similarity higher than a set threshold and corresponding third similarity;

generating a third difference level aiming at each feature word of each second type character string in the target weight item according to the third similarity and preset threshold information;

4. The method of claim 1, further comprising:

capturing all or specified technical effect descriptions from the target patent application to form a first technical effect set;

capturing all or appointed technical effect descriptions from all comparison files corresponding to the target patent application to form a second technical effect set; calculating a fourth similarity of the first set of technical effects to the second set of technical effects;

generating a fourth difference level between the target patent application and all comparison files according to the fourth similarity and preset threshold information;

and generating a fourth group of answer and debate advice information corresponding to the target patent application according to the fourth difference level.

5. The method according to any one of claims 1-4, further comprising:

capturing all or specified technical problem descriptions from the target patent application to form a first technical problem set;

capturing all or appointed technical problem descriptions from all comparison files corresponding to the target patent application to form a second technical problem set;

calculating a fifth similarity of the first technical problem set and the second technical problem set;

generating a fifth difference level between the target patent application and all comparison files according to the fifth similarity and preset threshold information;

and generating a fifth group of answer and suggestion information corresponding to the target patent application according to the fifth difference level.

6. The method of any one of claims 1-5, wherein the similarity is calculated based on one or more of cosine similarity, simple common words, edit distance, Hamming distance, Jacard similarity coefficient, Euclidean distance, Manhattan distance;

the method further comprises the following steps: positioning a right item containing a preset examination keyword from the examination opinion notice; and setting the similarity value of the rights item which contains the preset examination keyword and does not have the matched contrast file to be zero.

7. The method of claim 6, further comprising:

generating first answer suggestion information corresponding to the target patent application according to the first difference level corresponding to each target right item respectively, comprising:

when the first answer target information is acquired, generating an indication that a plurality of subordinate rights items with first difference levels of moderate differences or high differences are added to the independent rights items;

when the second answer target information is acquired, generating an indication that the independent right item is not modified;

when the third answer target information is acquired, an indication is generated that only one weight whose first difference level is a height difference is added to the independent weight.

8. An auxiliary analysis device for intelligently providing patent answer advice is characterized by comprising:

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of assisted analysis for intelligently providing patent answer suggestions according to any one of claims 1 to 7.

10. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of assisted analysis for intelligently providing patent answer suggestions as recited in any of claims 1-7.