Writing assisting method and device and storage medium

Abstract

The invention discloses a writing assistance method and device and a storage medium, and the method comprises the steps: reading a file name of a patent-related text, the file name comprising a file identifier, and the file identifier being associated with writing reference information of the patent-related text; acquiring the writing reference information associated with the file identifier; wherein the obtained writing reference information is displayed while the content of the patent related text is displayed. The information support capability of text editing can be improved, and the working efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a writing assistance method, device and storage medium. Background Art

[0002] Text editing is the daily work of most people in modern society, such as article editing, report writing, meeting minutes and instant message input.

[0003] Input method applications are essential tools for completing the above writing tasks. When the cursor of a text application or text input window is entered with pinyin or Wubi key information, an input method provides a candidate window with several candidate contents for the user to refer to and select. Once the user selects another candidate content, the selected candidate content will be filled in the text application or text input window.

[0004] Some input method applications also provide certain content association functions, but these content associations are mainly based on the user's input frequency to recommend words, and words with higher input frequency will be recommended first.

[0005] However, the inventors of the present application have discovered during long-term research and development that the efficiency of inputting content into a text is still too low and the accuracy is not high enough. Summary of the invention

[0006] The embodiments of the present application provide a writing assistance method, device and storage medium to solve the technical problems of low efficiency and low accuracy in text writing.

[0007] In order to solve the above technical problems, the first aspect of the present application provides a writing assistance method, which includes: reading the file name of a patent-related text, the file name includes a file identifier, and the file identifier is associated with the writing reference information of the patent-related text; obtaining the writing reference information associated with the file identifier; wherein, while the content of the patent-related text is displayed, the acquired writing reference information is displayed.

[0008] To solve the above technical problems, the second aspect of the present application provides a text writing assistance method, the method comprising: a server receives a file name sent by a client, the file name includes a file identifier, and the file identifier is associated with writing reference information of the text; the server obtains writing reference information associated with the file identifier; the server sends the writing reference information to the client, so that the client displays the acquired writing reference information while displaying the content of the text.

[0009] To solve the above-mentioned technical problems, the third aspect of the present application provides a text writing assistance method, the method comprising: using an input method to input content in a text opened by a text editing application; using a plug-in of the text editing application to obtain the content, and using at least part of the characters of the content as keywords to search for matching paragraphs or matching words and sentences in or outside the text; and displaying the matching paragraphs or matching words and sentences on the same screen as the content as writing reference information.

[0010] To solve the above technical problems, the fourth aspect of the present application provides a text writing assistance method, the method comprising: receiving a first content input in a text, or receiving a first content input in an input method interface; using the first content as a keyword, searching for matching paragraphs or matching words and sentences in the text or a designated document, the matching paragraphs or matching words and sentences include the first content and the second content, or the matching paragraphs or matching words and sentences include the second content and related content of the first content, the matching paragraphs or matching words and sentences are defined in the text or designated document by a boundary character, and the boundary character is a common character adjacent to the matching paragraph or matching word before or after; using the matching paragraphs or matching words and sentences as writing reference information or recommendation information, and displaying them on the same screen as the text.

[0011] To solve the above technical problems, the fifth aspect of the present application provides a computer device, which includes: a processor; a memory connected to the processor and used to store program instructions, which can be executed by the processor to implement the writing assistance method provided in the first aspect.

[0012] In order to solve the above technical problems, the sixth aspect of the present application provides a computer-readable storage medium, which is used to store program instructions, and the program instructions can be executed to implement the writing assistance method provided in the first aspect above.

[0013] The beneficial effect of the present application is that, different from the prior art, the embodiment of the present application utilizes the file naming rules with identifiers commonly adopted by enterprises, which can automatically extract the file identifier of the file name when editing text, and use the file identifier to automatically obtain relevant data within the enterprise itself or related enterprises, thereby providing stronger information support for text editing, eliminating the need for manual memory or search, improving work efficiency and input accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0015] Figure 1 It is a schematic diagram of an interface of an embodiment of a method for assisting writing of text related to the present patent application;

[0016] Figure 2 It is a schematic diagram of an interface of another embodiment of a method for assisting writing of text related to the present patent application;

[0017] Figure 3 This is a schematic diagram of an interface of an embodiment of the application writing assistance method;

[0018] Figure 4 It is a schematic diagram of an interface of another embodiment of the application writing assistance method;

[0019] Figure 5 It is a data structure diagram of an embodiment of a method for assisting writing of text related to the present patent application;

[0020] Figure 6 It is a data structure diagram of another embodiment of the method for assisting writing of the relevant text of the present patent application;

[0021] Figure 7 It is a schematic diagram of an example product of an embodiment of a method for assisting writing of related texts of the present patent application;

[0022] Figure 8 is a structural schematic diagram of an embodiment of a computer device provided by the present application;

[0023] Fig. 9 It is a structural schematic diagram of an embodiment of a computer-readable storage medium provided by the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] At present, part of the work of patent agents is to write patent documents, form patent-related texts, and then submit them as patent applications through official channels. Patent applications generally include invention applications, utility model applications or design applications. Among them, the patent-related texts involved in invention applications and utility model applications generally include abstracts, claims, specifications, etc. In patent agency firms, it is often necessary to represent several or even hundreds of different applicants in patent applications. Different applicants have different requirements for patent applications. Patent agents need to distinguish the different requirements of different applicants and write patents differently. However, in many cases, agents may forget the relevant requirements of applicants, or confuse the different requirements of different applicants, resulting in low writing efficiency, or the quality of the completed patent application documents does not meet the requirements of the applicants. On the other hand, for patent agents, it often takes several years of training to gain certain work experience to meet the requirements of the growing number of applicants, but all patent agents need to start working from zero experience. Although the documents completed by these junior agents are generally reviewed by internal teachers, before the review, junior agents have no idea where to start due to lack of experience and knowledge. Even if they write part of the content, they are not sure whether it is correct, and then revise it again and again, which is very inefficient.

[0027] In addition to the patent agency industry, for companies with office needs, text editing work is often related to data and information within their own company or related companies. When data and information support within the company or other companies is needed, they often need to retrieve files from the relevant database and then search manually, which is very inconvenient.

[0028] To solve the above technical problems, in one embodiment of the present application, a writing assistance method is proposed, which uses the existing naming rules of marked files in modern enterprises to automatically obtain relevant reference information to assist agents to write texts that meet the requirements with high quality and high efficiency. The method includes:

[0029] Step 100: reading a file name, where the file name includes a file identifier, and the file identifier is associated with writing reference information of the patent-related text;

[0030] See also Figure 1 In this embodiment, the user opens a text application or a third-party program and enters the text editing interface 100, and the system automatically extracts the file name 300 of the patent-related text. Alternatively, when the user inputs text using an input method in the text editing interface, the system automatically extracts the file name 300 of the patent-related text. Of course, the timing when the system automatically extracts the file name of the patent-related text is not limited to the above two situations. The system referred to in the embodiment of the present application is a program, application, plug-in or tool that implements the writing assistance method of the embodiment of the present application.

[0031] Step 200: Obtain the writing reference information associated with the file identifier;

[0032] The client can send the file name extracted by the system to the server, and the server searches for the writing reference information of the file identifier in the corresponding file name in the association relationship between the file identifier and the writing reference information, and returns it to the client.

[0033] Optionally, the association relationship between the file identifier and the writing reference information, as well as the collection of the writing reference information, is stored in advance on the server. The writing reference information may exist in the form of a file, that is, one file identifier is associated with one or more files. The writing reference information may also exist in the form of multiple information units stored in a file, and one file identifier is associated with one or more of the information units.

[0034] Writing reference information can be laws and regulations, process controls, writing requirements, writing skills, writing experience or banned words, etc.

[0035]

[0036] Table 1: The relationship between document identification and writing reference information

[0037] Table 1 is an example of the association between file identification and writing reference information. For ease of understanding, the file identification and writing reference are directly used as the two objects in the mapping relationship. In practice, one side of the association relationship is the customer number or application type, etc., and the other side is the writing reference information. In Table 1, the "CN" in the definition file identification "CNXYP202412345" represents China, "XY" represents the customer number, "P" represents the patent, "2024" represents the year, and the first number "1" following "2024" represents the application type, which is an invention application. The remaining digital sequence represents the number of this application. The server reads the file identification in the file name and obtains that the customer name is XY, so it obtains the specific requirements in the writing reference information "file a" and "file b" associated with the file identification through the association relationship. In addition, the priority in the association relationship represents the priority level of the corresponding writing reference information in subsequent display or other operations. The higher the priority, the higher the priority, the higher the priority display. For example, when the screen display area is insufficient, the writing reference information with a higher priority level is displayed first.

[0038]

[0039] Table 2: The relationship between document identification and writing reference information (Part 2)

[0040] Table 2 is another example of the association between file identifiers and writing reference information. The writing reference information of this association is divided into at least two categories. One is basic information, which can be referenced by all application documents, and the other is classified information. Only specific file identifiers are associated. Other file identifiers are not associated and will not be read by the system. For example, the file identifier CNXYP202418888 indicates that the corresponding application document is an invention application document, so the identifier is associated with information unit 1 of file a, but not with information unit 2. The file identifier CNXZP20242000 indicates that the corresponding application document is a utility model application document, so it is associated with information unit 1 and information unit 2 of file a.

[0041] After the writing reference information is returned to the client, the client displays the obtained writing reference information 201 while displaying the text content. The writing reference information 201 may be displayed in at least two optional ways:

[0042] 1. The text and writing reference information 201 do not affect each other and are displayed on the same screen. For example, the text and the file containing the writing reference information 201 are displayed side by side, or the text is mainly displayed, and the writing reference information is displayed in the form of a sidebar 200; if the sidebar 200 displays too much writing reference information and cannot be reasonably displayed on the screen, the writing reference information 201 with a high priority can be highlighted, or only part of the writing reference information 201 with a high priority can be displayed, or only part of the writing reference information 201 can be displayed. When the user clicks on a part of the displayed writing reference information 201, the system automatically expands and displays the undisplayed part of the writing reference information 201, replacing or covering the displayed content in other areas of the screen.

[0043] 2. While inputting content in the text, writing reference information is displayed in the form of content recommendation near the current cursor. Once the user selects a certain writing reference information, the writing reference information will be filled in behind the current cursor as part of the text. If the writing reference information is not selected, the writing reference information will change position as the cursor moves, and it will be displayed to the user for reference without blocking the user's line of sight or affecting the user's input. In addition, in addition to being associated with the file identifier, the writing reference information can also be associated with the user's input content in the text. For example, if the user enters "claims", the system will think that the user is writing claims, and therefore recommends relevant laws and regulations, writing experience, writing requirements, writing skills, etc. regarding the writing of claims.

[0044] Optionally, at least some embodiments of the present application are implemented using plug-ins of text editing applications, such as MICROSOTF WORD applications or WPS applications. These text editing applications are relatively closed, and generally can only be operated on these text editing applications themselves or the texts opened by plug-ins. For example, reading the file name of a text, reading the content entered into the text using an input method, allowing the text to be split-screen or superimposed in a window to display writing reference information, etc., can all be implemented using plug-ins supported by the text editing application.

[0045] Optionally, obtaining the writing reference information associated with the file identifier includes:

[0046] Step i: Obtaining customer information associated with the file identifier;

[0047] The server preselects and retains the definition rules of the file identifier and the association relationship between the file identifier and the customer information, parses the customer information therein through the definition rules of the file identifier, and then obtains the writing reference information based on the association relationship.

[0048] Step ii: obtaining the writing reference information associated with the customer information, wherein the writing reference information corresponding to at least two pieces of the customer information are different.

[0049] Optionally, the writing reference information corresponding to all customer information is different, but the writing reference information corresponding to some customer information may be the same, which is defined in specific circumstances.

[0050] Optionally, the writing reference information includes writing requirements, and the step of obtaining the writing reference information associated with the file identifier includes:

[0051] i: automatically modify the content of the patent-related text according to the writing requirements; or

[0052] ii: Mark out the parts of the patent-related text that do not meet the writing requirements or pop up a prompt.

[0053] This embodiment can achieve a higher degree of automation, allowing the system to review the text as an auditor, and further, can directly modify the text on behalf of the user. Specifically, the writing reference information can be pre-defined, and the parts that are easy for the computer to recognize and understand can be defined separately according to predetermined rules, so that the subsequent system can read and check the text according to the writing reference information. If it is found that the text does not meet the writing reference information, it will be modified according to the writing reference information. For example, if the writing reference information requires that certain words cannot appear, and these words need to be replaced with new words that meet the requirements, the system will automatically replace the relevant words in the text with new words that meet the requirements.

[0054] For parts that are inconvenient to modify automatically, the parts that do not meet the writing requirements can be marked in the text content or a pop-up window prompt can be displayed.

[0055] Optionally, in order to more accurately locate and write reference information, the file name of the patent-related text read includes:

[0056] Obtaining a module position of a current cursor in a patent-related text, wherein the module position includes at least one of an abstract module position, a claim module position, an invention title position, a technical field module position, a background technology module position, an invention or utility model content module position, a drawing description module position, and a specific implementation mode module position;

[0057] Among them, the invention content module can be further subdivided into the technical problem module (referred to as the technical problem module) that the invention or utility model requires to solve, the technical solution module, and the technical effect module.

[0058] The obtaining of the writing reference information associated with the file identifier includes:

[0059] Obtain the file identifier and the writing reference information associated with the module position of the current cursor in the patent-related text.

[0060] That is to say, when the patent-related text is a patent application document, the writing reference information corresponding to the position can be recommended based on the specific position of the current cursor (or mouse) in the patent application document. For example, if the current cursor is located at the claim module position, writing reference information related to claim writing is recommended. The method for determining which module position the current cursor is located at includes determining between which two module names of the patent application document the current cursor is located, and taking the module position corresponding to the previous module name as the current cursor position. For example, if the current cursor is located between the two names of Technical Field and Background Technology, it is considered that the current cursor is located in the technical field module. If there is no module name after the current cursor, it is judged to be the last module.

[0061] Optionally, the writing requirement includes that banned words cannot be used, and the step of obtaining the writing reference information associated with the file identifier includes:

[0062] i: Search the content of the patent-related text using the banned words as keywords;

[0063] For example, after processing the text, the user closes the text, and the system intervenes at this time. That is, after receiving the instruction to close the text, the system automatically pauses to close the text, obtains the writing reference information with the file identifier of the text, and after identifying that the writing reference information includes banned words, it searches the text with each banned word;

[0064] ii: marking the search results in the patent-related text, or replacing the results in the patent-related text with substitute words corresponding to the banned words, and each banned word is preset with at least one corresponding substitute word.

[0065] Optionally, in order to select an alternative word, before replacing the searched result with the alternative word corresponding to the banned word, the method includes:

[0066] i: positioning the current display position of the patent-related text to the searched result, and displaying at least two optional alternative words near the result;

[0067] This feature allows users to easily select the correct alternative word to replace all search results.

[0068] ii: receiving a first instruction to select one of the alternative words;

[0069] For example, if the user double-clicks one of the alternative words, a first instruction is generated.

[0070] The replacing the searched result with the substitute word corresponding to the banned word comprises: replacing the result with the selected substitute word in response to the first instruction.

[0071] Of course, the method of automatically modifying the content of the patent-related text according to the writing requirements is not limited to modifying banned words, but can also be to change multiple references in the claims to single references, modify incorrect reference relationships, modify typos, add "said" in front of all components that appear in the claims, modify incorrect labels or serial numbers, etc.

[0072] Optionally, in order to provide the user with information related to the current input during the writing process, the step of obtaining the writing reference information associated with the file identifier includes:

[0073] i: receiving the current content inputted in the display interface of the patent-related text;

[0074] For example, enter a technical term, a patent application number, a legal term, or even a paragraph.

[0075] ii: using at least a part of the current content as a keyword, searching for a document set corresponding to the current user group, where different user groups correspond to different document sets; or searching the current text;

[0076] The server pre-stores a document collection corresponding to the current user group, such as documents related to patent writing specifications, or patent documents that have been partially or fully represented by this user group, i.e., this patent agency, or documents such as customer requirements.

[0077] iii: Displaying the searched document set, the matching paragraphs or matching words and phrases matching the keyword in the current text.

[0078] For example, if the current input is "creativity", the discussion on creativity in the Patent Law, the Implementing Rules of the Patent Law and the Examination Guidelines can be searched, and these discussions can be extracted from the documents and displayed on the left or right side of the screen. For another example, if the current input is "electric vehicle", the patent documents that have been represented by this patent agency in part or in full can be automatically searched, and relevant patent documents on electric vehicles can be found, and a part of the abstract can be displayed on the left or right side of the screen.

[0079] Optionally, the process of searching for matching paragraphs or matching words and sentences that match the keywords can adopt different methods. It is relatively simple to obtain matching paragraphs, that is, as long as there is a keyword in a paragraph, the first carriage return character is identified in the text from the keyword, and at least the content between the keyword and the first carriage return character can be used as a matching paragraph. As for the sentences in the matching words and sentences, it is also relatively easy to obtain, that is, as long as there is a keyword in a sentence, the first punctuation mark is identified in the text from the keyword, and at least the content between the keyword and the first punctuation mark can be used as a matching sentence. For the words in the matching words and sentences, a word library can be obtained by segmenting the text, and the keywords can be matched in the word library. Alternatively, a simpler method is adopted, which does not require pre-configuration of the word library, but uses some text features to define some boundary symbols, and uses the boundary symbols to "capture" vocabulary.

[0080] For example, nouns are a type of vocabulary that needs to be "captured". In particular, there are a large number of nouns in patent-related texts that protect products. Due to the particularity of patent-related texts, there are a large number of "self-created" or "customized" nouns in patent-related texts. These "self-created" or "customized" nouns do not exist in dictionaries in the general sense, nor in professional dictionaries. Therefore, when writing patent-related texts, if you try to use the input method on the market to recommend these nouns, the effect is often very poor. The reason is that the input methods on the market generally use two methods to recommend vocabulary. One is to directly match the dictionary, and the other is to count the word frequency and recommend nouns based on the frequency of the word. The limitations of dictionaries have been described above, and counting word frequency also has limitations. Word frequency statistics are either network statistics for all users or local statistics for this article. The word frequency counted by the network does not match the nouns in this article, because the vocabulary of this article is insignificant in the vast amount of documents on the Internet, and the vocabulary of this article may not be input by input method. Local statistics only recommend vocabulary that has been input in this article, but for Pinyin input method, whether only the first pinyin or the full pinyin is input, if there are multiple words with the same first pinyin or the same full pinyin, accurate vocabulary recommendations are often not obtained. More importantly, almost all input methods only generate corresponding characters or words according to the user's keystrokes, and will not generate characters or words other than the keys. For example, when the user types the two first pinyins "zl" representing "patent", only recommendations such as "information", "instructions", and "patents" will appear, and there will be no associative recommendations such as "patent law" or "patent-related texts" other than the actual input, which makes it difficult to effectively improve text editing efficiency.

[0081] After research, the inventor of the present application realized that the reason why the input method has not actually implemented associative recommendations beyond actual input is that, first, the existing industry personnel have inertia of thinking, and second, it is difficult to obtain the optimal solution among multiple aspects such as accurate recommendation, vocabulary demarcation and cost. Regarding accurate recommendation, the current input method has a relatively high accuracy in short vocabulary recommendation, but as the length of the vocabulary increases, the accuracy drops drastically to almost unusable. The reason is that there are too many words with the same full pinyin or the same initial pinyin. For this reason, the recommendation accuracy cannot be 100% for a single word. When multiple words form the associative recommendation mentioned above, through the combination probability analysis of probability theory, it can be concluded that even if the accuracy of a single word is relatively high, when multiple words are combined into a long word, the recommendation accuracy probability of the long word can become very low. Secondly, it is difficult to demarcate a single short word, and it is even more difficult when trying to demarcate a long word. Of course, it can be analyzed using the currently popular natural language processing methods or through AI models, but these tools are often costly or have poor real-time performance. The speed of inputting content using an input method generally depends on the speed of typing on the keyboard, and the input method must keep up with the speed of typing on the keyboard. This limits the application of high-throughput word segmentation tools and forms a research bottleneck for long word recommendations.

[0082] Therefore, optionally, the embodiment of the present application proposes a writing assistance method with high recommendation accuracy, reasonable vocabulary demarcation, low cost and fast response, including:

[0083] i. receiving a first content input in a text, or receiving a first content input in an input method interface;

[0084] Optionally, you can receive the first content entered in the text using the input method, or receive the first content entered in the input method interface using the input method. Receiving the first content entered in the text using the input method means that after the first content is entered in the text using the input method, the first content is obtained using a third-party program such as a plug-in of a text application. And receiving the first content entered in the input method interface using the input method means that when using the input method, the first content entered in the input method interface is obtained using the input method itself. For the Pinyin input method, the first content appears in the candidate window of the input method interface as a candidate word for the user to select.

[0085] ii. Using the first content as a keyword, searching for matching paragraphs or matching words in the text or specified document, the matching paragraphs or matching words include the first content and the second content, or the matching paragraphs or matching words include the second content and the related content of the first content, the matching paragraphs or matching words are defined in the text or specified document by delimiting characters, and the delimiting characters are common characters before or after adjacent matching paragraphs or matching words;

[0086] There are at least two ways to implement this step. The first way is to use the input method to use the first content as a keyword in the text or specified document to search for matching paragraphs or matching words and sentences, and display the matching words and sentences or matching paragraphs in the form of candidate words in the interface of the input method to be selected and filled in the text. That is, inputting the first content in the text, obtaining the first content (optional), searching for matching paragraphs or matching words and sentences, and displaying matching paragraphs or matching words and sentences to be selected and filled in the text are all completed by the input method; see Figure 3 When inputting text 210 in text 110 using pinyin input method 310, the first letters 320 of "ZL" are typed in the input method interface, and the first content 330 "patent" will appear. By directly searching in text 110 with "patent" as the keyword, matching phrases 340 such as "Patent Law" and "Patent-related documents" can be obtained.

[0087] Or the second method is to use a plug-in of a text editing application to search for matching paragraphs or matching words in a text or a specified document, and display matching words or matching paragraphs in the form of candidate words in the plug-in interface to be selected and filled into the text. That is to say, inputting the first content in the text can be completed by the input method, and other steps, such as obtaining the first content, searching for matching paragraphs or matching words, and displaying matching paragraphs or matching words to be selected and filled into the text, are completed by the plug-in of the text editing application. Figure 4 , is a schematic diagram of using the input method 500 and the plug-in 600 of the text editing application program to input the text 230. When the text 230 is inputted with the pinyin input method 500, the two first letters "ZL" 510 are typed in the input method interface, and multiple candidate words "patent", "material", "consciousness", etc. will appear. At this time, if the candidate word "patent" is selected, "patent" will be inputted into the text 230 as the first content 330. At this time, the input method interface is closed, and the plug-in of the text editing application program searches the text 2300 with "patent" as the keyword, and can obtain matching words 610 "Patent Law", "Patent-related documents", etc., which are displayed in the suggestion window 600 for the user to select to input the text 230.

[0088] Matching paragraphs or matching words and sentences include the first content and the second content, indicating that the search results are longer words or sentences than the first content, rather than just recommending words that are actually typed on the keyboard as in current input methods. Optionally, the first content and the second content are adjacent to each other, and the second content is located after the first content. For example, if the word "patent" is actually input, the second content can be "law", "related text" or "application document", etc. Of course, the first content can also be located after the second content.

[0089] Matching paragraphs or matching words and phrases are defined in the text or specified document by delimiting characters, which means that matching paragraphs or matching words and phrases can be located and delimited directly by using ready-made characters in the text or specified document without natural language processing or AI model analysis. These ready-made characters are named delimiting characters in this article because they can delimit and locate words and phrases in the text, such as nouns. Because these ready-made characters are usually adjacent to matching paragraphs or matching words and phrases and used in conjunction with them, they can also become universal characters. For example, delimiting characters include the first universal characters that appear in a sentence in the patent-related text: any one of "includes", "has", "includes", and "provides", and can also include the second universal characters that appear in a sentence in the patent-related text: any one of punctuation marks and numbers. For example, in the product claims, the claim limitation structure usually adopts an open limitation, that is, "includes", "has", "provides", or "includes" is used to introduce the limited structure, as shown in the following independent claims:

[0090] 1 .A sort of Advertising module , characterized in that it includes:

[0091] B1 ;

[0092] B3 ,include c3 , c3 have d3 ;

[0093] B6 ,include c7 , c7 have d7 , B6 one end connection Said b1, the other end passes through Said d3 ;

[0094] B8 , Insert Said d7, and located at Said C3 back to back Said b1 side .

[0095] In the above independent claims, B1, B3, B6, and B8 are all components of the advertising module (for the convenience of description, English letters and numbers are used to replace the actual component names), and they are all nouns. Because the delimiting character "including" is specifically used to introduce the defined structure, and it must be located before the defined B1, B3, B6, and B8, it belongs to the front universal character. Similarly, "having", "having", etc. also belong to the front universal character. After these nouns B1, B3, B6, and B8 are introduced, they are usually followed by punctuation marks or conjunctions such as "and", "with", and "and", so punctuation marks, conjunctions, labels, etc. belong to the back universal characters. Moreover, the front universal characters and the back universal characters appear in the same sentence. For example, the above independent claims can be regarded as a sentence, and the entire paragraph has only one period. Of course, in some scenarios, the words ending with commas, semicolons, and commas will also be regarded as a sentence. The main purpose of using front universal characters and back universal characters to locate matching words and sentences is to determine the first appearance of words in the claim, because the first appearance of words such as nouns in the claim is easier to delimit than the second and subsequent words. For the scenario where the second content is located behind the first content, the first content and the following universal characters can usually be used to delimit the second content, that is, the content sandwiched between the first content and the following universal characters is read out and displayed as the second content for recommendation.

[0096] iii. Use the matching paragraphs or matching words and sentences as writing reference information or recommended information, and display them on the same screen as the text.

[0097] As mentioned above, after finding the second content, the second content can be displayed separately as a matching paragraph or matching phrase on the same screen as the text, or the first content and the second content can be combined into a matching paragraph or matching phrase and placed in the suggestion window as candidate content or candidate words. After the user selects them, they can be filled into the text.

[0098] Obviously, because no high-cost tools are used for vocabulary capture, but the content of the text itself is used to match paragraphs or match sentence boundaries, long vocabulary recommendations are provided accurately and at a very low cost. Real-time recommendations can be made without affecting input speed, greatly improving text editing efficiency.

[0099] Optionally, the number of the matching paragraphs or matching words is several, and after displaying the matching paragraphs or matching words, the method includes:

[0100] i: receiving a second instruction to select one of the matching paragraphs or matching words;

[0101] After observation, the user feels that one of the matching paragraphs or matching words is more appropriate, so the user double-clicks the matching paragraph or matching word with the mouse.

[0102] ii: Combine the current content with the selected matching paragraph or matching phrase in response to the second instruction.

[0103] When the user selects a certain matching paragraph or matching phrase, there are two ways to combine the current content with the selected matching paragraph or matching phrase. First, directly put all the selected matching paragraph or matching phrase behind the current cursor in the text for the user to edit; second, only fill in the content after the keyword in the matching paragraph or matching phrase behind the current cursor in the text, so that the filled content is combined with the content of the text.

[0104] By directly recommending matching paragraphs or matching phrases, users can be enabled to avoid retyping too much content, greatly improving the input efficiency.

[0105] Optionally, if the user thinks only a part of the content in the matching paragraph or matching phrase is needed, after displaying the matching paragraph or matching phrase, it includes:

[0106] i: Receive a third instruction to select a part of the content in the matching paragraph or matching phrase;

[0107] For example, the user uses the mouse to select a part of the content in the matching paragraph or matching phrase.

[0108] ii: Combine the selected part of the content with the matching paragraph or matching phrase in response to the third instruction.

[0109] For example, after the selection is completed and the mouse is released, the system automatically fills the selected content behind the current cursor in the text.

[0110] Optionally, in order to perform better matching, searching for the document set corresponding to the current user group with at least a part of the current content as the keyword includes:

[0111] Search for the document set corresponding to the current user group with the keyword obtained after denoising processing, and the denoising processing includes removing "the", "this", "of", "the above" or "the following".

[0112] Because there are special regulations on the text content in patent application documents. For example, in the claims, when a name appears for the second time, "the" needs to be added in front. Therefore, when the system uses this name as a keyword, it may also include "the" as part of the keyword by accident, but "the" may not exist in the document set corresponding to the current user group, resulting in a matching failure. Therefore, performing denoising processing before searching can make the search operation more accurate and smooth.

[0113] Optionally, when the number of the matching paragraphs or matching phrases is several, displaying the matching paragraphs or matching phrases includes:

[0114] The matching paragraphs or matching words are sorted according to the distance from the current cursor position, and the matching paragraph or matching word closest to the current cursor is placed at the top of the sorting and displayed in the candidate window below the current cursor.

[0115] When users input text, they usually focus on describing the same thing in one paragraph or several adjacent paragraphs. Therefore, the probability of the thing appearing in the same content area is relatively high. Therefore, when users input the corresponding text of the thing, it is preferred to put the nearest matching paragraph or matching phrase at the top of the sorting list to facilitate user viewing and selection.

[0116] Optionally, the displaying of the matching paragraph or matching phrase includes, before, or after:

[0117] The matching paragraph or matching phrase placed at the first position in the sorting list and the remaining matching paragraphs or matching phrases are displayed distinctively, and the page where the current cursor is located and the page where the text of the matching paragraph or matching phrase placed at the first position in the sorting list is located are displayed separately in a split screen or overlay display in a window.

[0118] When the user is viewing the searched matching paragraphs or matching words, in order to guide the user's viewing, the matching paragraph or matching word placed at the top of the sort and the remaining matching paragraphs or matching words can be displayed distinctively; at the same time, in order to allow the user to know more about the source of the searched matching paragraphs or matching words, the screen can be split, with one screen interface displaying the page where the current cursor is located, and the other screen interface displaying the page where the text of the matching paragraph or matching word placed at the top of the sort is located, so that the user can learn more information.

[0119] Optionally, the matching paragraph or matching phrase that is ranked first among the plurality of matching paragraphs or matching phrases is set as a default selected item, and after the page where the current cursor is located and the page where the text of the matching paragraph or matching phrase that is ranked first is located is displayed, the following is included:

[0120] A fourth instruction for reselecting the matching paragraph or matching word is received, the reselected matching paragraph or matching word is displayed distinctively, and the page where the content of the reselected matching paragraph or matching word is located is displayed.

[0121] If the user wants to know the content of the page containing other matching paragraphs or matching words after split-screen viewing, the user can select other matching paragraphs or matching words. After selection, the screen will refresh to display the page containing the re-selected matching paragraph or matching word content.

[0122] Optionally, if the screen is already in a split-screen state before it is split, the split-screen content of the page where the matching paragraph or matching word content is located will replace the original split-screen content. After the user fills the selected content behind the current cursor, the system can be restored to the original state, that is, the non-split-screen state.

[0123] Optionally, in order to facilitate users to better obtain relevant information, after opening the current file, the system obtains or allows the current file to automatically obtain links to other files in the same folder, and arranges these other demarcation links on the top or side of the current file. Click these links and the files of these links will be displayed in the split-screen position. Generally speaking, related files will be stored in the same folder, such as placing the relevant technical briefing documents, comparative documents, and drawings of the same patent application in the same folder. In the prior art, after opening the briefing document, if the user wants to open files in the same folder, he needs to switch windows and open other files. Because window switching will cause the user to operate too much, and sometimes switch incorrectly, resulting in switching back and forth and wasting time. The embodiment of the present application automatically obtains links to other files in the same folder, arranges these other demarcation links on the top or side of the current file, and clicks these links to display these linked files in the split-screen position, without the need to switch windows back and forth, saving time and having high accuracy.

[0124] Optionally, enter text in the current file and search the same folder with the entered text. If there are identical texts in the same folder, the searched content and its page will be displayed on the right side of the split screen, which is helpful for patent agents to refer to the relevant information of the briefing book for writing. Optionally, after the automatic split screen, the content of the split screen will be adaptively resized for easy viewing by users.

[0125] Optionally, in order to minimize user operations, after receiving the current content input on the display interface of the patent-related text, the following is included:

[0126] In response to whether the distance between the current cursor and the bottom of the current text is less than a threshold, the current text is automatically scrolled backward so that the distance between the current cursor and the bottom of the current text is not less than the threshold.

[0127] That is, since the current text will automatically scroll backwards when the current cursor position is too low, after the text scrolls, the current cursor follows the scrolling and returns to the appropriate position, so that the user does not need to frequently use the mouse or other buttons to manually scroll the text page, thus minimizing user operations. This embodiment is not limited to application to patent-related texts, and any text type can be applicable, and this embodiment may not be associated with any previous embodiment.

[0128] Optionally, displaying the searched document set, the matching paragraphs or matching words and sentences matching the keyword in the current text includes:

[0129] One of the matching paragraphs or matching words matching the keyword in the searched document set or the current text is pre-selected and filled into the text input space behind the current cursor, and if there is more than one matching paragraph or matching word matching the keyword in the searched document set or the current text, the remaining matching paragraphs or matching words are placed in a candidate window, and if a fifth instruction for selecting the next matching paragraph or matching word is received, the next matching paragraph or matching word is highlighted in the candidate window. This embodiment may not be associated with any of the previous embodiments.

[0130] Existing input method applications will pop up a candidate window when the user is typing, but before the user confirms, both the typing content and the candidate content appear in the pop-up candidate window. Only when the user selects the candidate content will the selected candidate content be filled in the text input space behind the current cursor. During this process, the user's line of sight will switch between the candidate content on the left side of the current cursor and the candidate content in the candidate window. The embodiment of the present application pre-selects matching paragraphs or matching words and phrases and fills them into the text input space behind the current cursor, so that the user's line of sight may not have to switch between the candidate content on the left side of the current cursor and the candidate content in the candidate window. The user's line of sight only needs to focus on the left and right of the current cursor, saving the user's energy.

[0131] Optionally, in some embodiments of the present application, it is necessary to switch between the existing input method and the system used in the embodiments of the present application, which involves the analysis, application, and problem avoidance of "focus" in the user interface (UI). In user interface design, focus is a very important concept, which refers to the control or element that can currently receive user input. When a control has focus, the user can interact with it directly through the keyboard, such as entering text, navigating options through arrow keys, etc. The concept of focus is not limited to keyboard input, but can also be extended to click events on a touch screen or other forms of user input.

[0132] It can be seen that when the existing input method and the system used in the embodiment of the present application are used simultaneously, the capture of focus is a necessary operation. It is necessary not only to ensure that the existing input method can accurately and timely capture the focus, but also to ensure that the system of the embodiment of the present application can accurately and timely capture the focus, so as not to cause the input method to be unable to be called up in time to input content during the text input process, unable to call up the suggestion window generated by the system of the embodiment of the present application, or unable to successfully call up the input method again after the suggestion window generated by the system of the embodiment of the present application appears. The suggestion window generated by the system of the embodiment of the present application is defined as being able to display matching paragraphs or matching words, or writing reference information and other contents. The inventor of the present application found when using the system of the embodiment of the present application that when the input method is used to input content and the suggestion window is called up, when the suggestion window is ignored and the input method is used to continue to input content, the first character entered (hereinafter referred to as "key" or "key message") is "swallowed", that is, the input method cannot be called up in time, resulting in the second and third characters entered being displayed in the input method window after the input method is called up later, and the first character entered at the beginning does not appear. In some fast input scenarios, the second and third characters may be "swallowed".

[0133] More specifically, the normal operation scenario should be:

[0134] When the suggestion window is called up, it is necessary to ensure that the focus is on the suggestion window to facilitate switching up and down options. Therefore, when the keyboard is pressed at this time, the input method will inevitably be called up on the suggestion window. If you ignore the suggestion window and continue to input content using the input method, the suggestion window needs to disappear, and the focus is transferred to the text application, and the input method needs to be displayed as a candidate window floating state.

[0135] However, due to the design of the computer operating system itself, or the incompatibility between the input method and the computer operating system, problem 1 occurs: the input method locates the candidate window coordinates through the placeholder frame (representing the focus) of the text, and saves the position to be inserted where the current cursor is located in the text. When the user selects an option content in the candidate window of the input method, such as pressing the space key to confirm, the placeholder frame disappears, and the option content selected in the candidate window is sent to the position to be inserted in the text (the position behind the placeholder frame). According to the embodiment of the present application, the option content sent to the position to be inserted in the text will evoke the suggestion window, and the focus will be switched to the suggestion window (the placeholder frame is initially bound to the suggestion window). When the suggestion window is evoked, if you ignore the suggestion window and continue to input content using the input method, that is, press the keyboard, triggering the suggestion window to disappear. When the suggestion window disappears, the input method loses the binding object. At this time, although the focus will return to the text application, the position to be inserted in the input method is lost, triggering the candidate window of the input method to close, that is, this time the key only triggers the window to close, and the activation of the input method will be terminated due to the window closing, resulting in "swallowing words".

[0136] The above technical problems are difficult to find, mainly because users use different types of computers or their versions, different operating systems or their versions, different installed input methods or their versions, and different application environments in their computers. Some users may not find the above technical problems all the time. Therefore, the inventor of this application accidentally discovered the above technical problems during a large number of attempts and switching between different computers for research and development, and set out to improve them.

[0137] Optionally, a solution provided by an embodiment of the present application is that, at the same time or after the system of the embodiment of the present application evokes the suggestion window, at the moment of pressing the keyboard, it records which key is pressed, and then allows the input method to trigger the candidate window to close. Then the previously recorded keys are sent to the operating system again, and a typing event is triggered again, and the input method is activated for the second time. This will not cause the problem of swallowing words, and it will make it look like the candidate window of the input method has never disappeared. Of course, optionally, at the moment of pressing the keyboard, it can be determined based on the speed of the user's input to record which keys are pressed, or not to record which keys are pressed, so that no matter how fast the user's input speed is, the input method can completely and correctly capture the characters corresponding to the keys actually entered by the user when the input method is activated for the second time. In order to ensure that at the same time or after the system in the embodiment of the present application triggers the generation of the suggestion window, the number of keys pressed is recorded at the moment the keyboard is pressed, and no key information is missed, the timing can be started when the system triggers the generation of the suggestion window, and the keys pressed can be recorded within a relatively generous preset time length, which is defined as the first key combination (including the case where there is only one key information). Then, when the input method is activated for the second time, new keys are recorded in real time, which is defined as the second key combination (including the case where there is only one key information), and the first key combination and the second key combination are spliced ​​in sequence, and the adjacent keys between the two key combinations are deduplicated. For example, if the first key combination is AB and the second key combination is B, they are spliced ​​together as AB, and the pinyin or letter B is deduplicated.

[0138] Then, in this process, if the input method closes itself because the position to be inserted is lost, and then the recorded keys are entered immediately, the current cursor (placeholder box) will look normal when typing, but when the user selects an option in the candidate window of the input method, such as pressing the space bar to confirm, the current cursor will jump to the "0" position at the beginning of the document.

[0139] The inventor of the present application speculates that when the input method was invoked for the second time, the insertion position created for the first time was used, but at this time the insertion position had been lost, that is, it became the parameter "null", causing the input method to mistakenly pass null to the text application, causing the text application's selection to be affected by null and suddenly jump to the beginning of the document (position 0).

[0140] There are many factors that cause the above-mentioned technical problems, and each system and application is independent of each other, and will not tell each other their core technology or technical details. At the same time, there is no suitable or realistic third party to effectively coordinate the interaction between the two parties or multiple parties. Therefore, the technical problems are difficult to be discovered, and after the technical problems are discovered, they are also very difficult to solve. After long-term thinking, the first solution proposed by the inventor of the present application is to refresh the cache information of the input method after entering the content in the text opened in the text editing application using the input method until the suggestion window is called up, so that the input method refreshes the binding required insertion position based on the current cursor position. At this time, the candidate window to be inserted when the input method is called up again is correct, and pressing the space bar will not cause the current cursor (placeholder box) in the text to jump to the beginning of the text.

[0141] The second solution is to send the previously recorded keys to the operating system again to trigger a typing event. The principle of this method is that since the loss of the position to be inserted causes problems, it is better not to let the input method enter the position to be inserted in the first place. At the moment when an option in the candidate window generated by the input method is selected, or when the suggestion window is called up, the input method is switched off or disabled. At this time, the user thinks that he is typing in the Chinese input method state and presses the a key, but actually enters the English a.

[0142] Then the background closes the suggestion window, swallows the English a, switches the input state of the input method to Chinese, enters an a in the Chinese state, and evokes the Chinese a. Since the insertion position has not lost the binding process from beginning to end, null will not appear, and it will not jump to the beginning of the text. The whole process is imperceptible to the user.

[0143] The third solution is to close the input method after the first input and before the input method gets the typed message again, so that the input method is not bound to the focus on the suggestion window, that is, the input method is only bound to the focus before the suggestion window is called up and when it is called up for the second time after the suggestion window is closed. In this way, the focus position bound to the input method can always remain unchanged, and it is not easy to cause the input method to bind to the focus on the suggestion window and then the suggestion window disappears, causing the input method to lose the binding object and causing the input position to be affected when the input method is called up for the second time.

[0144] Optionally, if there is too much writing reference information to be fully displayed on the screen, the display of the acquired writing reference information includes: scrolling and highlighting the writing reference information on the display interface of the patent-related text.

[0145] Optionally, the step of obtaining the writing reference information associated with the file identifier includes:

[0146] i: receiving a sixth instruction to close the patent-related text;

[0147] ii: In response to the sixth instruction, a pop-up window is displayed to display the writing reference information before closing the patent-related text.

[0148] Displaying the writing reference information in a pop-up window before closing the patent-related text can remind the user in case the user forgets to write the reference information, so that the user will not miss out on important information such as customer requirements due to unclear understanding of the writing reference information before and after closing the patent-related text.

[0149] Optionally, the writing reference information includes a data structure, which defines several elements of the protected subject matter and their relationships, as well as a set of elements and a set of relationships that constitute each claim. For example, the elements of a product claim generally include components, assemblies or structures of a product, and components or structures are generally composed of components, etc. The relationships of a product claim generally include positional relationships, connection relationships, actuation relationships, signal relationships, or electromagnetic field relationships, etc. For another example, the elements of a method claim generally include the steps of the method, and the relationships of a method claim generally include the order of the steps.

[0150] Optional, such as Figure 2 As shown, in order to facilitate the editing of the data structure, the first area 1000 and the second area can be displayed in the software interface. The first area 1000 is used to edit the data structure, and the second area is used to wait for the display or display of the already formed or claims, or to display the content of the technical briefing, or to display the prior art. The second area displays the content of the technical briefing, and can read the technical briefing, prior art and other related technical contents while conceiving the elements and their relationships of the claims, so as to facilitate editing the set of elements and the set of relationships in the first area 1000, and define the elements and their relationships involved in each claim. The second area displays the content of the prior art, which is convenient for comparing the differences between the invention and the prior art, and for better understanding the invention.

[0151] Optionally, the second area can switch to display the claims, technical disclosure document, and prior art, or can display at least two of the above three in parallel. If the claims have not yet been formed, only the technical disclosure document and prior art can be displayed.

[0152] Optionally, the second area can be hidden in the interface. For example, after being hidden, moving the mouse to the sidebar triggers the second area to be displayed in the interface. At the same time, the first area 1000 is reduced, and the visual information of the data structure in the first area 1000 is adaptively adjusted in size and position so as to be adaptively displayed in the first area 1000.

[0153] Optionally, the technical disclosure document and prior art in the second area can also be set to be hidden and invisible, and the mouse moves to the corresponding position of the sidebar or the top or bottom area to trigger the corresponding technical disclosure document or prior art to be displayed on the interface, or to zoom in and out the display area. Of course, the size of the first area 1000 can also be adjusted or even hidden.

[0154] Optional, such as Figure 5 As shown, a tree diagram or a flowchart of a chain structure can be edited in the first area, and the information and its relationship in the edited chain structure diagram constitute the data structure 3000 of the embodiment of this application. Optionally, the data structure 3000 in the first area is displayed in the form of a tree diagram or a flowchart. Taking a tree diagram as an example, the tree diagram has a root node 3100 and a branch node 3200. The root node 3100 is used to edit and display the subject matter protected by the claims, such as the largest product name involved in the invention. For example, if a mobile phone is invented, the root node 3100 can be edited as a mobile device or a smart terminal. The first-level branch node can be the next level of the root node 3100, and the second-level components such as circuit boards, camera components, and communication components can be edited. The second-level branch node is the next level of the root node 3100, and the third-level components such as the radio frequency circuit and antenna in the communication component can be edited, and so on, until all elements involved in the invention are edited, and a complete structural decomposition is formed in the form of a tree diagram. The above root nodes 3100 and branch nodes are collectively referred to as nodes herein.

[0155] The process of completing the tree diagram is also a process in which the agent repeatedly considers, revises, and gradually improves the claim structure and layout in a visual manner. Compared with directly writing claims in text editing software, the embodiment of the present application makes writing easier to start, clearer, more comprehensive, and less error and omission.

[0156] Optionally, during the process of editing the data structure, the software receives a first instruction for text editing, node addition, node deletion, or node position change of a selected node in the tree diagram or flow chart; that is, you can directly right-click in the first area or click the corresponding operation button on the interface to generate a first instruction for text editing, node addition, or node position change of the selected node.

[0157] The software responds to the first instruction and performs text editing, node addition, node deletion, or node position change operations on the selected node in the tree diagram or flow chart. For example, right-click the first area and select the option "node addition", then the software adds a node to the next-level node position or the previous-level node position of the area where the right button is located or the node pointed to by the right button. Alternatively, drag the third-level node a to the area where the second-level node is located, and the system generates a first instruction. The software responds to the first instruction and moves the third-level node a to the second-level node position, and node a becomes a second-level node. The original second-level node can coexist with node a at the same level, or it can swap positions with node a. At the same time, the software can automatically adjust the shape or size of other nodes in the tree diagram or the tree diagram, so that the tree diagram adapts to the changes in node a.

[0158] Optionally, after the lowest level node is edited, the software can automatically add a lower level node to be edited based on the lowest level node, waiting for possible node additions, without the need to manually add nodes. When reading the data structure subsequently, nodes with unedited text will be automatically ignored.

[0159] Optionally, after performing text editing, node addition, or node position change operations on a selected node in a tree diagram or a flow chart, including:

[0160] The software receives a second instruction to define a relationship between selected nodes in the tree diagram. After editing the elements of the claim in the tree diagram, the relationship between the elements needs to be defined, so the software receives the corresponding second instruction.

[0161] See also Figure 6 , the software responds to the second instruction and draws a line connecting the selected nodes in the first area, one end of the line connects the selected node, such as A11, and the other end is a text input box, and the current cursor is located in the text input box. If the number of selected nodes is greater than or equal to two, one or more lines connecting all the selected nodes are drawn in the first area, one end of each of the lines connects the corresponding selected node, such as A12, and the other end is a text input box, and the current cursor is located in the text input box.

[0162] If a line is drawn connecting two or more nodes, a text box will be automatically displayed in the middle of a line or at the adjacent ends of several lines, and the current cursor is located in the text input box. For example, Figure 3 If one end of the middle line is connected to B2 and the other end is connected to A12, a text box will be displayed in the middle of the line or an area where text can be edited will be formed.

[0163] Optionally, if the tree diagram cannot fit in the screen of the first area, the content may be automatically reduced or part of the content may be automatically hidden, or the scope of the first area may be automatically expanded.

[0164] The purpose of drawing lines is to visually see which element or elements have a relationship. At the same time, lines also define the links between elements and their relationships, and the links between different elements. These link information constitutes part of the data structure. Letting the text box appear and the current cursor be in the text box simplifies the operation. There is no need to move the current cursor and enter the editing state. You can enter the editing state by default after drawing the line, and you can directly enter text in the text box.

[0165] Optionally, the number of text input boxes is one or two. When the number is one, the text input box is divided into a relationship input area and a technical problem input area. When the number is two, one text input box is used to input the relationship and the other text box is used to input the technical problem.

[0166] For example, you can select any two or more nodes by pressing "shift" or other control keys on the keyboard. The software will automatically draw a line to connect the text boxes corresponding to the two nodes. The current cursor will automatically fall into any position in the text box, or you can click on one of the text boxes to enter a description of the relationship between the selected nodes, and click on another text box to enter the technical problem to be solved.

[0167] Optionally, you can edit several technical issues and their relationships for the tree diagram, set the order of each technical issue, or directly enter "first technical issue", "second technical issue", etc. in different text boxes to represent different claims so that the software can recognize them. Each technical issue corresponds to a claim. After defining the order of the technical issues, the software can sort the subsequently formed claims according to the order of the technical issues.

[0168] The data structure of the embodiment of the present application is not limited to the above-mentioned form, and may also include a graph and elements and relationships on the graph. Figure 4 , the user can directly draw a line on the diagram, the starting point of the line is the position of the component corresponding to the product in the diagram, and the end point is outside the product. The user can edit the name of the component at the end point. In order to reflect the hierarchical relationship of the components, you can also start with the names of multiple parallel components and continue to draw lines pointing to the name of the same upper-level component. In addition, you can continue to draw lines to edit the relationship between components, and finally form a data structure.

[0169] The above data structure can be searched out when the relevant content is input in the current text as reference information for writing. For example, if the user edits a data structure related to or similar to the above data structure in the current text, the system can automatically recommend it, and the user can directly use the recommended data structure and modify or edit it based on it.

[0170] The following is a brief description of how to use the above data structure:

[0171] S200: Read data structure;

[0172] After the data structure is edited, or after the data structure is obtained, click the "OK" button or press the function key, etc., and the system generates a third instruction. The software responds to the third instruction to read the data structure, or the software directly reads the data structure after obtaining the data structure, and parses the data structure to obtain the set of elements and the set of relationships that constitute each claim. If the data structure contains information about technical problems, the technical problems, the set of elements corresponding to the technical problems, the set of relationships, and the sorting information of the technical problems are obtained.

[0173] Optionally, after parsing the data structure, a protected subject in the data structure is determined according to a second preset rule, a first claim is determined under the determined protected subject, and a set of elements and a set of relationships associated with the first claim are read.

[0174] For example, the second preset rule includes first finding the technical problem ranked first, then finding the technical problem ranked first in the parsed data structure, reading the first technical problem and its associated set of elements and set of relationships. The technical problem ranked first means that it is determined as a protected subject when editing the data structure, so finding the technical problem ranked first means determining the first claim under the determined protected subject.

[0175] Then, according to the second preset rule, for example, the technical problems ranked second, third, etc. and the sets of elements and the sets of relationships associated therewith are read in sequence.

[0176] Optionally, there may be two or more protected subjects in the data structure, and the independent claims corresponding to each protected subject can be marked, such as marked with different letters. The serial numbers of the first set of claims are all named in the form of Am, and m is a variable Arabic numeral. The serial numbers of the second set of claims are all named in the form of Bn, and n in the independent claims of the second set of claims is obtained by adding one to the Arabic numeral of the last claim of the first set of claims. The two sets of claims are distinguished by the first letters A and B. The serial numbers of other sets of claims are similar, and the order of independent claims can be based on the order of the first letters. The next independent claim with the last first letter is ranked after the previous set of claims corresponding to the independent claim with the first first letter. In this way, the software can easily and accurately sort the claims, determine which one is the independent claim, and determine which are the dependent claims that are subordinate to which independent claim. If a combination of letters is used to mark the claims, the order of technical issues can be omitted.

[0177] Of course, the serial number naming method is not limited to this, as long as the rules are predetermined and the software can recognize it.

[0178] S300: Forming a corresponding claim from a set of elements and a set of relationships corresponding to each claim according to a first preset rule;

[0179] The first preset rule is to use a set of elements and a set of relationships to construct a rule that meets at least some of the formal requirements of the claim, such as the format, sentence order, punctuation marks, etc. required by the claim.

[0180] Optionally, the order in which the elements in the set of elements associated with the first claim appear in the first claim is determined using the set of relations associated with the first claim.

[0181] For example, see Figure 7 , and the data structure of the following table:

[0182]

[0183]

[0184] Table 3: Collection of elements

[0185]

[0186]

[0187] Table 4: Collection of relations

[0188] Tables 3 and 4 are optional data structures in the embodiments of the present application. In Table 3, the largest protected subject is the advertising module in the a column, and the next-level elements are the drawing board, frame, pins, latches, elastic parts and safety ropes in the b column. The next-level elements are the various components in the c column, and the most subordinate are the various components in the d column. Among them, the strip board and decorative parts in the c column belong to the drawing board in the b column, and the relationship between other components is similar. When the software reads the data structure in the form of a table, it will parse out that the strip board and decorative parts belong to the drawing board, and the first mounting hole belongs to the strip board based on the regional relationship of the table and the regional position of the elements in the table. The mounting plate belongs to the frame, the plate hole and the first rope hole belong to the mounting plate, and so on. The relationship set of Table 2 reflects the different relationships between the elements in Table 1. Table 1 and Table 2 are associated through the address of the column of Table 1, such as B6.

[0189] In Table 4, the first technical problem, which is the technical problem corresponding to the first claim, is “easy to disassemble and assemble”, and the set of relationships is “one end of B6 is connected to b1, and the other end passes through d3, b8 is inserted into d7, and is located on the side of c3 facing away from b1”. According to the order in which the elements appear in the first claim, the template corresponding to the first claim is applied to form the organizational structure of the elements and the organizational structure of the relationships of the first claim.

[0190] The first claim is an independent claim, so its template can be defined as follows:

[0191] 1 .A sort of Advertising module , characterized in that it includes:

[0196] The italic and underlined serial numbers "1" and "advertising module" mentioned above are variables, and the rest are template constants. The serial numbers are given according to the rules. For example, the first claim outputs "1", the second claim outputs "2", and so on. "Advertising module" is the protected subject, which can be obtained from the set of elements in Table 2. The leftmost element in the table, or the root element of the chain structure, is taken as one of the protected subjects. Of course, the elements in the middle area of ​​the chain structure can also be taken as protected subjects, which can be defined and set according to the situation. The template ends with a period. Only one period is allowed in a claim, and the period is placed at the end of the template. Between "it is characterized by" and "includes", and between "includes" and "." is the fillable space for the remaining technical features.

[0197] Optionally, the set of elements includes the set of product elements, the set of relationships includes the set of element relationships, the first claim is an independent claim, and the next line of the independent claim and before the period are defined as the upper necessary elements (elements) filled in with the lowest necessary elements (elements). Optionally, in Table 4 "Set of Relationships", the necessary elements and their relationships reflect the lowest necessary elements and their relationships, and when necessary, the upper necessary elements and their relationships. It should be noted that whether the "necessary elements and their relationships" referred to here are necessary depends on the technical problem to be solved. Therefore, the "necessary elements", "necessary components", and "necessary relationships" referred to in this article actually refer to "elements", "components", and "relationships", respectively. For different technical problems, at least some of the "necessary elements", "necessary components", and "necessary relationships" are different.

[0198] The method of first determining the lowest-level essential elements and using the set of relationships associated with the first claim to determine the order in which the elements in the set of elements associated with the first claim appear in the first claim may include:

[0199] By using the set of relationships associated with the first claim, all elements in the first claim are constructed into a subject-object sorting link, and the elements are sorted in the reverse order of the sequence of the elements in the subject-object sorting link.

[0200] For example, all the elements and their relationships in the first claim are "one end of B6 is connected to b1, and the other end passes through d3, b8 is inserted into d7, and is located on the side of c3 facing away from b1".

[0201] Optionally, in order to ensure that the constructed subject-object sorting link meets the requirements, the software automatically checks whether a closed loop is achieved in each claim. The closed loop conditions include whether all elements within a claim and between different claims are related to at least one other element, and whether there is only one subject-object sorting link. Otherwise, a prompt is given that the closed loop cannot be achieved.

[0202] The software (system) further analyzes all the elements and their relationships in the first claim and obtains two links "b8-d7(b1), b6-b1(d3)". The analysis shows that these two links constitute a single link through b1, which meets the requirements. The lowest-level necessary elements of the single link or the two links are b1, d7, and d3. It should be noted that the lowest-level necessary elements referred to here refer to the lowest level of the elements involved in the current claim.

[0203] Sort the necessary components at the bottom layer. Since b1 is the object of the two links, it ranks first. d7 and d3 are in a parallel relationship in the link. It is necessary to use the order of appearance of the necessary relationship to sort them. d3 is ranked after b1, and d7 is ranked after d3.

[0204] Determine all upper-level necessary components of the lowest-level necessary components. There is no upper-level necessary component of b1, which is b1 itself. The upper-level necessary components of d7 are c7 and b6. The upper-level necessary components of d3 are c3 and b3. The principle of determination is to obtain upward in a single chain and discard branches. For a chain structure, upward acquisition means obtaining from the node at the upper level.

[0205] The software then determines the order of all upper-level necessary elements: b1, b3, b6, b8.

[0206] Continue to fill in the above-determined necessary elements and their necessary relationships in the independent claim writing template. Optionally, according to the order of the lowest level necessary elements, list the inclusion relationship of the upper level necessary elements and the corresponding necessary relationships in sections. Optionally, in the inclusion relationship, all holes, cavities, grooves, gaps, spaces, channels, airways, liquid channels, and openings use "having" or "forming", and others use "including" by default. According to the above method, the first claim obtained is as follows:

[0207] 1 . A Advertising module , characterized in that it includes:

[0208] B1 ;

[0209] B3 , including c3 , the c3 has d3 ;

[0210] B6 , including c7 , the c7 has d7 , the B6 one end connection the b1, the other end passes through the d3 ;

[0211] B8 , Insert the d7, and located at the C3 back to back the b1 side .

[0212] The italicized and underlined content above are all variables, and the rest are template constants. It is not necessary to add "the" before the first occurrence of an element. For non-first occurrences of an element, "the" needs to be added before it.

[0213] It can be understood that the first preset rule is not unique and can be set differently according to needs. For example, it is not necessary to consider whether a closed loop is achieved in each claim, and the conditions for a closed loop may not be included only in one claim, whether all elements between different claims are related to at least one other element, etc. Another example is that by introducing an intelligent large model and inputting the elements and their relationships, the claims can be obtained.

[0214] The embodiments of the present application also provide a method for assisting in writing a text, including:

[0215] i: The server receives the file name sent by the client, and the file name includes a file identifier, and the file identifier is associated with the writing reference information of the text;

[0216] ii: The server obtains the writing reference information associated with the file identifier;

[0217] iii: The server sends the writing reference information to the client so that the client can display the obtained writing reference information while displaying the content of the text.

[0218] Please refer to Figure 8 , Figure 81 is a schematic diagram of a computer device 50 according to an embodiment of the present application. In one embodiment, the computer device 50 includes a memory 51 and a processor 52 coupled to each other, and the processor 52 is used to execute program instructions stored in the memory 51 to implement the steps of any of the above-mentioned writing assistance method embodiments. In a specific implementation scenario, the computer device 50 may include, but is not limited to: a microcomputer, a server, and in addition, the computer device 50 may also include a mobile device such as a laptop computer and a tablet computer, which is not limited here.

[0219] Specifically, the processor 52 is used to control itself and the memory 51 to implement the steps of any of the above-mentioned writing assistance method embodiments. The processor 52 can also be called a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with signal processing capabilities. The processor 52 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 52 can be implemented by an integrated circuit chip.

[0220] See also Fig. 9 , Fig. 9 It is a structural diagram of an embodiment of a computer-readable storage medium provided by the present application. The computer-readable storage medium 60 of the embodiment of the present application stores a program instruction 61, and when the program instruction 61 is executed, it implements the method provided by any embodiment of the writing auxiliary method of the present application and any non-conflicting combination. Among them, the program instruction 61 can form a program file and be stored in the above-mentioned computer-readable storage medium 60 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) executes all or part of the steps of each implementation method of the present application. The aforementioned computer-readable storage medium 60 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, and a tablet.

[0221] In one embodiment, the application writing assistance method is executed through program instructions, which are installed in the existing text editing software in the form of plug-ins and act on the patent-related text opened by the text editing software to implement the above-mentioned patent-related text writing assistance method.

[0222] In one embodiment, the present application writing assistance method is executed by program instructions, which are independently executed as computer software and at least include text editing functions. The program instructions act on the patent-related text in the computer software to implement the above-mentioned patent-related text writing assistance method.

[0223] In one embodiment, the present application writing assistance method is executed by program instructions, and the program instructions include at least two parts, one of which is located in the user's computer device, and the other is located in the server. At least one step in the above-mentioned patent-related text writing assistance method embodiment is executed by the server and can return a result. The user communicates with the server and obtains the result to perform other steps to implement the above-mentioned patent-related text writing assistance method.

[0224] In one embodiment, the present application writing assistance method is executed through program instructions, all of which are located locally on the user's computer and are executed by the user's computer to implement the writing assistance method for the above-mentioned patent-related text.

[0225] In one embodiment, the application writing assistance method is entirely executed on a server, and the execution result is displayed through the user's computer, ie, the client.

[0226] It can be understood that the embodiment of the present application utilizes the file naming rules with identifiers commonly adopted by enterprises. It can automatically extract the file identifier of the file name when editing text, and use the file identifier to automatically obtain relevant data within its own enterprise or related enterprises, thereby providing relevant and strong information support for text editing, eliminating the need for manual memory or search, and improving work efficiency.

[0227] When the embodiments of the present application are applied to the patent writing assistance scenario, optionally, not only can the patent agent get information guidance like a senior teacher in real time during the writing process without manual help, but also provide real-time help on how to write, how to write, and how to revise; optionally, the patent agent can also understand the requirements of applicants, firms and other relevant parties in a timely manner without manual help during the writing process, so as not to forget the requirements of applicants or firms and cause customer complaints or criticisms; optionally, during the writing process or at the end, the written text can also be modified or prompted by default or user-defined requirements without the patent agent noticing, which is equivalent to providing patent agents with a tireless and stable writing assistant in real time to assist in checking and revising Change; Optionally, since the system can automatically use at least a part of the input content as a keyword to search the current file or server-related text in real time, compared with the existing input method that can only provide recommendations for common words or high-frequency words, the recommendation mechanism of the embodiment of the present application is the proximity principle or the early principle. The proximity principle is based on the fact that users will enter several identical contents in the same text area. The early principle is that in the claims, the name of the thing will be described first, and then other relationships will be described. Therefore, by obtaining the first appearance position of the thing, the boundary of the thing name can be accurately defined, and search results with very high relevance and high accuracy to the text can be obtained. Moreover, the search results are not limited to words, but can also be paragraphs, sentences or data structures, which greatly improves the input efficiency.

[0228] The terms "first", "second", "third" in this application are only used for descriptive purposes and cannot be understood as indicating the quantity of the indicated technical features. Thus, the features defined as "first", "second", "third" can expressly or implicitly include at least one of these features. In the embodiments of the present application, all directional indications (such as up, down, left, right, front, back ...) are only used to explain the relative positional relationship, motion conditions, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions. The process, method, system, product or equipment such as including a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or equipment.

[0229] The above are merely embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for assisting the writing of patent-related texts, characterized in that: include: Reading a file name of a patent-related text, wherein the file name includes a file identifier, and the file identifier is associated with writing reference information of the patent-related text; Obtaining the writing reference information associated with the file identifier; Wherein, while the content of the patent-related text is displayed, the acquired writing reference information is displayed.

2. The method according to claim 1, characterized in that The obtaining of the writing reference information associated with the file identifier includes: Obtaining customer information associated with the file identifier; The writing reference information associated with the customer information is obtained, and the writing reference information corresponding to at least two pieces of the customer information are different.

3. The method according to claim 1, characterized in that The writing reference information includes writing requirements, and the step of obtaining the writing reference information associated with the file identifier includes: Automatically modify the content of the patent-related text according to the writing requirements; or Mark out the parts of the patent-related text that do not meet the writing requirements or pop up a prompt.

4. The method according to claim 3, characterized in that The writing requirement includes that banned words cannot be used, and the step of obtaining the writing reference information associated with the file identifier includes: Searching the content of the patent-related text using the banned words as keywords; The search results are marked in the patent-related text, or the results in the patent-related text are replaced with substitute words corresponding to the banned words, and each banned word is preset with at least one corresponding substitute word.

5. The method according to claim 4, characterized in that The step of replacing the searched result with the substitute word corresponding to the banned word comprises: Positioning the current display position of the patent-related text to the searched result, and displaying at least two optional alternative words near the result; receiving a first instruction to select one of the alternative words; The replacing the searched result with the substitute word corresponding to the banned word comprises: replacing the result with the selected substitute word in response to the first instruction.

6. The method according to claim 1, characterized in that The step of obtaining the writing reference information associated with the file identifier includes: Receiving current content inputted into the display interface of the patent-related text; Using at least a part of the current content as a keyword, searching for a document set corresponding to the current user group, where different user groups have different document sets; or searching the current text; The searched document set and the matching paragraphs or matching words and sentences matching the keyword in the current text are displayed.

7. The method according to claim 6, characterized in that The number of the matching paragraphs or matching words is a certain number, and after the matching paragraphs or matching words are displayed, the following steps are performed: Receiving a second instruction to select one of the matching paragraphs or matching words and phrases; In response to the second instruction, the current content is combined with the selected matching paragraph or matching phrase.

8. The method according to claim 6, characterized in that After displaying the matching paragraphs or matching words and sentences, the following steps are included: receiving a third instruction for selecting a portion of the matching paragraph or the matching phrase; In response to the third instruction, the selected part of the content is combined with the matching paragraph or matching phrase.

9. The method according to claim 6, characterized in that The step of searching for a document set corresponding to the current user group by using at least a portion of the current content as a keyword includes: The keywords obtained after denoising are used to search for the document set corresponding to the current user group, wherein the denoising includes removing "said", "the", "of", "above" or "below".

10. The method according to claim 6, characterized in that The number of the matching paragraphs or matching words and sentences is a plurality, and displaying the matching paragraphs or matching words and sentences includes: The matching paragraphs or matching words are sorted according to the distance from the current cursor position, and the matching paragraph or matching word closest to the cursor is placed at the top of the sorting and displayed in the candidate window below the cursor.

11. The method according to claim 10, characterized in that The matching paragraphs or matching words are displayed simultaneously, before or after: The matching paragraph or matching phrase placed at the first position in the sorting list and the remaining matching paragraphs or matching phrases are displayed distinctively, and the page where the current cursor is located and the page where the text of the matching paragraph or matching phrase placed at the first position in the sorting list is located are displayed separately in a split screen or overlay display in a window.

12. The method according to claim 11, characterized in that The first-ranked matching paragraph or matching phrase among the plurality of matching paragraphs or matching phrases is set as a default selected item, and the page where the current cursor is located and the text where the first-ranked matching paragraph or matching phrase is located are displayed includes: A fourth instruction for reselecting the matching paragraph or matching word is received, the reselected matching paragraph or matching word is displayed distinctively, and the page where the content of the reselected matching paragraph or matching word is located is displayed.

13. The method according to claim 10, characterized in that After receiving the current content inputted in the display interface of the patent-related text, the step includes: In response to whether the distance between the current cursor and the bottom of the current text is less than a threshold, the current text is automatically scrolled backward so that the distance between the current cursor and the bottom of the current text is not less than the threshold.

14. The method according to claim 6, characterized in that The step of displaying the searched document set and the matching paragraphs or matching words and sentences matching the keyword in the current text includes: One of the matching paragraphs or matching words matching the keyword in the searched document set or the current text is pre-selected and filled into the text input space behind the current cursor, and if there is more than one matching paragraph or matching word matching the keyword in the searched document set or the current text, the remaining matching paragraphs or matching words are placed in a candidate window, and if a fifth instruction to select the next matching paragraph or matching word is received, the next matching paragraph or matching word is highlighted in the candidate window.

15. The method according to claim 1, characterized in that The displaying of the acquired writing reference information includes: scrolling and highlighting the writing reference information on a display interface of the patent-related text; or The step of obtaining the writing reference information associated with the file identifier includes: receiving a sixth instruction to close the patent-related text; In response to the sixth instruction, displaying the writing reference information in a pop-up window before closing the patent-related text; The file name of the patent-related text read includes: Obtaining a module position of a current cursor in a patent-related text, wherein the module position includes at least one of an abstract module position, a claim module position, an invention title position, a technical field module position, a background technology module position, an invention content module position, a drawing description module position, and a specific implementation mode module position; The obtaining of the writing reference information associated with the file identifier includes: Obtain the file identifier and the writing reference information associated with the module position of the current cursor in the patent-related text.

16. The method according to claim 6, characterized in that The writing reference information includes a data structure, which defines several elements of the protected subject matter and their relationships, and defines a set of the elements and a set of the relationships constituting each claim; The step of obtaining the writing reference information associated with the file identifier includes: The set of the elements and the set of the relationships corresponding to each of the claims are formed into a corresponding claim according to a first preset rule.

17. The method according to claim 16, characterized in that The reading of the data structure includes: determining a protected subject in the data structure according to a second preset rule, determining a first claim under the determined protected subject, and reading the set of elements and the set of relationships associated with the first claim.

18. The method according to claim 17, characterized in that The step of forming a corresponding claim from the set of elements and the set of relationships corresponding to each claim according to a first preset rule comprises: Determine the order in which the elements in the set of elements associated with the first claim appear in the first claim by using the set of relations associated with the first claim; According to the order in which the elements appear in the first claim, a template corresponding to the first claim is applied to form the organizational structure of the elements and the organizational structure of the relationships of the first claim.

19. The method according to claim 18, characterized in that The set of elements includes a set of product elements, the set of relationships includes a set of element relationships, and the determining, using the set of relationships associated with the first claim, the order in which the elements in the set of elements associated with the first claim appear in the first claim comprises: By using the set of the relationships associated with the first claim, all the elements in the first claim are constructed into a subject-object sorting chain, and the elements are sorted in the reverse order of the order of the elements in the subject-object sorting chain.

20. A text writing assistance method, characterized in that: include: The server receives a file name sent by the client, wherein the file name includes a file identifier, and the file identifier is associated with the writing reference information of the text; The server obtains writing reference information associated with the file identifier; The server sends the writing reference information to the client, so that the client displays the acquired writing reference information while displaying the content of the text.

21. A text writing assistance method, characterized in that: include: Use the input method to enter content in the text opened in the text editing application; Obtaining the content using a plug-in of the text editing application, and using at least part of the characters of the content as keywords to search for matching paragraphs or matching words in or outside the text; The matching paragraphs or matching words and sentences are used as writing reference information and displayed on the same screen as the content.

22. The method according to claim 21, characterized in that The step of displaying the matching paragraphs or matching words as writing reference information together with the content on the same screen includes: Receiving a second instruction to select one of the matching paragraphs or matching words and phrases; In response to the second instruction, the current content is combined with the selected matching paragraph or matching phrase.

23. The method according to claim 21, characterized in that After searching for a matching paragraph or a matching phrase in or outside the text, the method further comprises: calling up a suggestion window to display the matching paragraph or the matching phrase; The process from inputting content in the text opened by the text editing application using the input method to calling up the suggestion window includes: refreshing the cache information of the input method so that the input method refreshes the position to be inserted in the text where the current cursor is located based on the current cursor position; or At the same time or after the suggestion window is called up, the key pressed is recorded at the moment of pressing the keyboard, and then the input method triggers the candidate window to close, and the previously recorded key is sent to the operating system again to trigger a typing event and activate input; or After the input method is used to input content for the first time and before the input method obtains the input message again, the input method is closed so that the input method is not bound to the focus on the suggestion window.

24. A writing assistance method, characterized in that: include: Receiving a first content input in a text file, or receiving a first content input in an input method interface; Using the first content as a keyword, searching for a matching paragraph or a matching phrase in the text or a designated document, wherein the matching paragraph or the matching phrase includes the first content and the second content, or the matching paragraph or the matching phrase includes the second content and the related content of the first content, and the matching paragraph or the matching phrase is defined in the text or the designated document by a delimiter character, and the delimiter character is a common character before or after the matching paragraph or the matching phrase; The matching paragraphs or matching words and sentences are used as writing reference information or recommendation information and displayed on the same screen as the text.

25. The method according to claim 24, characterized in that The delimiting characters include the first common characters appearing in a sentence in the patent-related text: any one of "include", "have", "include", and "have", and also include the second common characters appearing in a sentence in the patent-related text: any one of punctuation marks and numbers.

26. The method according to claim 24, characterized in that The receiving of the first content input in the text, or the receiving of the first content input in the input method interface comprises: receiving the first content input in the text using the input method, or receiving the first content input in the input method interface using the input method; The searching for matching paragraphs or matching words and phrases in the text or designated document, using the matching paragraphs or matching words and phrases as writing reference information or recommendation information, and displaying the matching paragraphs or matching words and phrases on the same screen with the text comprises: searching for matching paragraphs or matching words and phrases in the text or designated document using the input method, and displaying the matching words and phrases or matching paragraphs in the form of candidate words in the interface of the input method, to be selected and filled into the text; or The plug-in of the text editing application is used to search for matching paragraphs or matching words in the text or specified document, and the matching words or matching paragraphs are displayed in the form of candidate words in the interface of the plug-in to be selected and filled into the text.

27. A computer device, characterized in that: The computer device comprises: processor; A memory, connected to the processor, for storing program instructions, wherein the program instructions can be executed by the processor to implement the writing assistance method as described in any one of claims 1-26.

28. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program instructions, and the program instructions can be executed to implement the writing assistance method according to any one of claims 1-26.

Images