Acquisition system of final application text
By designing a system for obtaining the final application text, the problems of inefficiency and low accuracy in the prior art are solved, text screening based on the needs of candidate objects is realized, and the efficiency and accuracy of acquisition of the final application text are improved.
Patent Information
- Application Number
- CN202510241491.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-03
- Publication Date
- 2025-06-13
AI Technical Summary
In the prior art, determining the final application text is inefficient and inaccurate, mainly due to the failure to perform text screening based on the needs of candidate objects.
A final application text acquisition system is designed, and through a processor and memory stored with a computer program, the following steps are implemented: obtain the candidate text corresponding to the target text and the candidate object, and use different processing methods to compare the target text with the candidate text according to the needs of the candidate object to obtain the final application text.
By classifying and hierarchical division of policy texts, screening based on the needs of candidates has improved the efficiency and accuracy of obtaining the final application text.
Smart Images
Figure CN120144747A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of text processing, and particularly to a system for obtaining a final application text. Background Art
[0002] In the context of the current global economic integration and the rapid change of the policy environment, there are more and more development opportunities and challenges. In order to promote the development of specific industries, encourage technological innovation, optimize the industrial structure and other goals, governments and regional organizations of various countries frequently introduce various policy measures. These policies often include a series of specific standards and requirements, aiming to screen eligible objects to enjoy policy dividends. However, due to the large amount of content included in the policies and the large number of corresponding achievements of enterprises or relevant personnel, how to accurately match and determine the final application text has become an urgent problem to be solved.
[0003] In the prior art, the method for determining the final application text is as follows: manually, by reading policy documents one by one, manually comparing the standards therein with one's own situation, and through manual interpretation and analysis to understand the specific content and requirements of the policy so as to determine the final application text. Due to the huge amount of data, the text screening based on the needs of candidate objects is not considered, resulting in low efficiency in obtaining the final application text, and different matching methods are not adopted based on the different needs of candidate objects, reducing the accuracy of obtaining the final application text. Summary of the Invention
[0004] In view of the above technical problems, the technical solution adopted by the present invention is as follows: a system for obtaining a final application text, the system includes: a processor and a memory storing a computer program. When the computer program is executed by the processor, the following steps are implemented:
[0005] S100, obtaining a target text, where the target text is a criterion text including several rules formulated to evaluate whether a target object meets a certain condition.
[0006] S200, obtaining a candidate text corresponding to a candidate object, where the candidate object is an object to be matched with the target text to confirm whether it meets the requirements corresponding to the target text, and the candidate text is a text corresponding to a series of achievements of the candidate object within a historical time period.
[0007] S300, when the candidate object has a target demand, using a first processing method to compare the target text with the candidate text to obtain the final application text corresponding to the candidate object.
[0008] S400, when the candidate object does not have a target demand, using a second processing method to compare the target text with the candidate text to obtain the final application text corresponding to the candidate object.
[0009] Compared with the prior art, the present invention has obvious beneficial effects. By means of the above technical solution, a system for obtaining a final application text provided by the present invention can achieve quite remarkable technological progress and practicality, and has wide industrial utilization value. It has at least the following beneficial effects:
[0010] The present invention is a system for obtaining a final application text. The system includes: a processor and a memory storing a computer program. When the computer program is executed by the processor, the following steps are implemented: obtaining a target text, obtaining a candidate text corresponding to a candidate object, when the candidate object has a target requirement, comparing the target text with the candidate text by using a first processing method to obtain the final application text corresponding to the candidate object, and when the candidate object does not have a target requirement, comparing the target text with the candidate text by using a second processing method to obtain the final application text corresponding to the candidate object. It can be seen that the present invention classifies policy texts, grades the classified policy texts, and filters based on the requirements of candidate objects to determine the final application text, improving the efficiency of obtaining the final application text. Based on the different requirements of candidate objects, different matching methods are used for their result texts to obtain the final application text, making the accuracy of the obtained final application text relatively high.
[0011] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the following preferred embodiments are specifically given and described in detail in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] Figure 1 It is a flowchart of a computer program executed by a system for obtaining a final application text provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0013] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of the present invention.
[0014] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0015] Embodiment
[0016] This embodiment provides a system for obtaining a final application text. The system includes: a processor and a memory storing a computer program. When the computer program is executed by the processor, the following steps are implemented, as Figure 1 shown:
[0017] S100, obtain a target text, where the target text is a criterion text including several rules formulated to evaluate whether a target object meets a certain condition.
[0018] Specifically, the target text is, for example, a target text such as a policy. Among them, the target object can be an enterprise, a team or an individual.
[0019] S200, obtain a candidate text corresponding to a candidate object, where the candidate object is an object to be matched with the target text to confirm whether it meets the requirements corresponding to the target text, and the candidate text is a text corresponding to a series of achievements of the candidate object within a historical time period.
[0020] Specifically, the candidate object is an object to be matched with the target text to confirm whether it meets the requirements corresponding to the target text, such as: a company, an enterprise and a scientific researcher.
[0021] Specifically, the candidate text can be understood as the achievements corresponding to the candidate object, such as candidate texts such as patents, software copyrights and qualification certificates.
[0022] Specifically, the time span corresponding to the historical time period is the same as the time span required in the target text.
[0023] S300, when the candidate object has a target requirement, use a first processing method to compare the target text with the candidate text to obtain the final application text corresponding to the candidate object.
[0024] Specifically, the target requirement is the target score corresponding to the candidate object, where the target score is the score that the candidate object wants to confirm for matching the target text.
[0025] Specifically, in S300, the final application text is obtained through the following steps:
[0026] S301, based on the target text, obtain several first intermediate texts, where the first intermediate texts are texts obtained by splitting the target text based on a preset category.
[0027] Specifically, the preset category is the theme category involved in the preset application, such as preset categories like patents, software copyrights, and qualification certificates.
[0028] S302, based on several first intermediate texts, obtain the list of candidate texts corresponding to the candidate text, where the list of candidate texts includes several candidate texts, and the candidate texts are first intermediate texts that meet the preset conditions obtained based on several second intermediate texts corresponding to the candidate text, and the second intermediate texts are texts obtained by splitting the candidate text based on the preset category.
[0029] Specifically, the preset condition is that the similarity between the category corresponding to the second intermediate text and the category corresponding to the first intermediate text is 1, where the category corresponding to the second intermediate text is one of the preset categories, and the category corresponding to the first intermediate text is one of the preset categories.
[0030] S303, obtain the list of target application texts corresponding to the list of candidate texts to obtain the final application text, where the list of target application texts includes several target application texts, each candidate text corresponds to a target application text, and the final application text includes all the target application texts in the list of target application texts.
[0031] Specifically, S303 also includes the following steps:
[0032] S1, based on the candidate text, obtain the set of target title lists E = {E 1 , E 2 , E 3}, E 2 = {E 2 1 , ……, E 2 i , ……, E 2 n}, E 3 = {E 3 1 , ……, E 3 i , ……, E 3n}, E 3 i = {E 3 i1 , ……, E 3 ij , ……, E 3 im(i)}, E 1 is the first target title, E 2 i is E 1 the corresponding second target title list E 2 the i-th second target title in, E 3 ij is E 2 i the j-th third target title in the corresponding third target title list.
[0033] Specifically, the first target title is the first-level title in the text to be selected.
[0034] Specifically, the second target title is the second-level title under the first-level title in the text to be selected.
[0035] Specifically, the third target title is the third-level title under the second-level title in the text to be selected.
[0036] Furthermore, those skilled in the art know that any method of determining a title from a text in the prior art falls within the protection scope of the present invention and will not be elaborated here.
[0037] S2. According to E and the second intermediate text corresponding to the text to be selected, obtain the target priority list set F = {F 1 , ……, F i , ……, F n}}, F i = {F i1 , ……, F ij , ……, F im(i)}, F ij is the target priority corresponding to the candidate path corresponding to E 3 ij .
[0038] Specifically, the candidate path corresponding to E 3 ij is E 1 - E 2 i - E 3 ij , where E 1 is connected to E 2 i , E 2 iConnected to E 3 ij wherein, it can be understood that a tree - like structure model including N candidate paths is formed based on E. Among them, in the tree - like structure model, E 1 is connected to each second target title in E 2 and E 2 i is connected to each third target title in E 3 i .
[0039] Specifically, N is the number of candidate paths in the target key model, and N meets the following conditions:
[0040] N = ∑ n i＝1 m(i).
[0041] Specifically, F is obtained through the following steps in S2 ij :
[0042] S21, obtain the first key statement list corresponding to the second intermediate text of the candidate text. Among them, the first key statement list includes several first key statements, and the first key statements are key statements obtained from the second intermediate text corresponding to the candidate text.
[0043] Specifically, the first key statements are statements obtained by dividing the second intermediate text corresponding to the candidate text according to punctuation marks.
[0044] Specifically, those skilled in the art know that any method of obtaining key statements from text in the prior art falls within the protection scope of the present invention and will not be elaborated here.
[0045] S22, obtain the second key statement list corresponding to E 3 ij wherein, the second key statement list includes several second key statements, and the second key statements are key statements obtained from the key text corresponding to E 3 ij The key text corresponding to E 3 ij is the text between the third target title corresponding to E in the candidate text and the third target title corresponding to E 3 ij E 3 i(j+1) is the (j + 1) - th third target title in the third target title list corresponding to E 3 i(j+1) is 2 i .
[0046] Specifically, the method for obtaining the second key statement is the same as that for obtaining the first key statement.
[0047] S23. Obtain the first candidate score η corresponding to E according to the first key statement list and the second key statement list. 3 ij where η meets the following conditions: 1 ij η 1 ij
[0048] η 1 ij = ∑ s(ij) r＝1 λ r ij where λ r ij is the number of the first key statements in the first key statement list that the r-th second key statement corresponding to E matches, r = 1... s(ij), and s(ij) is the number of the second key statements in the second key statement list corresponding to E. 3 ij 3 ij
[0049] Specifically, the method for the first key statement to match the second key statement is to judge by obtaining the similarity between the first key statement and the second key statement. Among them, those skilled in the art know that any method for calculating the similarity between statements in the prior art falls within the protection scope of the present invention and will not be elaborated herein.
[0050] S24. Obtain the third key statement list corresponding to E, where the second key statement list includes several second key statements, and the third key statement is any key statement other than the second key statement among the key statements obtained from the key text corresponding to E. The key text corresponding to E is the text between the second target title corresponding to E in the candidate text and the second target title corresponding to E, and E is the (i + 1)-th second target title in the second target title list E corresponding to E. 2 i 2 i 2 i 2 i 2 i+1 2 i+1 1 2
[0051] S25. Obtain the first candidate score ξ corresponding to E according to the first key statement list and the third key statement list.2 i The corresponding second candidate score η 2 i , where η 2 i meets the following conditions:
[0052] η 2 i = ∑ f(i) e＝1 β e i , β e i is the number of the first key statements in the first key statement list that the e-th third key statement corresponding to E 2 i matches, e = 1... f(i), and f(i) is the number of the third key statements in the third key statement list corresponding to E 2 i corresponding.
[0053] Specifically, the method for the third key statement to match the first key statement is the same as that for the second key statement to match the first key statement.
[0054] S26, obtain F 1 ij according to η 2 i and η ij ij , where F ij
[0055] meets the following conditions: ij F 1 ij = η 2 i .
[0056] S3, obtain the specified condition text list set Q 3 corresponding to E 3 = {Q 3 1 , ……, Q 3 i , ……, Q 3 n}, Q 3 i = {Q 3 i1 , ……, Q 3 ij , ……, Q 3 im(i)}, Q 3 ij is E 3 ijThe corresponding list of specified condition texts, where the list of specified condition texts includes a plurality of specified condition texts, and the specified condition texts are conditional statements with judgment properties obtained based on the text between two adjacent third target headings in the text to be selected.
[0057] Specifically, the specified condition text can be understood as follows: in a text to be selected, there will be text corresponding to the previous heading between two adjacent third headings. Among these texts, there will be certain conditional statements. For example, if the number of patent applications in the mechanical field is 3 or more, it is recorded as 3 points; if the number of patent applications in the mechanical field is less than 3, it is recorded as 1 point, and so on.
[0058] S4. According to the specific target requirement and Q 3 , obtain the target application text corresponding to the text to be selected. Among them, the second intermediate text corresponding to the text to be selected is sequentially compared with the list of specified condition texts in Q 3 , and the intermediate scores are obtained sequentially until the sum of the obtained intermediate scores is not less than the target score to determine the target application text. Among them, the target order is the order in which the target priorities in F are sorted from large to small. The intermediate score is the total score corresponding to the third target heading obtained by matching the second intermediate text corresponding to the text to be selected with the specified condition texts included in Q 3 ij .
[0059] Specifically, the specific target requirement is the score that a candidate object obtained from the target requirement wants to confirm for matching the first intermediate text under a specific preset category.
[0060] Specifically, those skilled in the art know that any method of condition matching based on text description in the prior art falls within the protection scope of the present invention and will not be elaborated here.
[0061] Specifically, the target application text is the text that meets the requirements of the text under the determined third target title selected from the second intermediate text corresponding to the candidate text. It can be understood that: after sorting the target priorities in F from largest to smallest, the third target titles corresponding to the target priorities will also obtain a new sorting order. Starting from the third target title corresponding to the largest target priority, the second intermediate text corresponding to the candidate text is matched with several specified condition texts corresponding to the third target title corresponding to the largest target priority. This third target title corresponds to a score. Using the same method, in order, the score corresponding to the third target title corresponding to the second sorted target priority is obtained, and several scores will be obtained. When the sum of the obtained scores is not lower than the target score, the content under the third target title corresponding to the obtained scores is obtained, and the text that meets the requirements of these contents is selected from the second intermediate text corresponding to the candidate text as the target application text.
[0062] As described above, classifying the policy text, grading the classified policy text, and screening based on the needs of the candidate object to determine the final application text improve the efficiency of obtaining the final application text. Through natural language processing technology, the target text is deeply analyzed and multi-source heterogeneous data is integrated, making the accuracy of the obtained final application document relatively high.
[0063] S400. When the candidate object has no target needs, the second processing method is used to compare the target text with the candidate text to obtain the final application text corresponding to the candidate object.
[0064] Specifically, the target application text is obtained through the following steps in S400:
[0065] S401. Based on the target text, several first intermediate texts are obtained, where the first intermediate text is the text obtained by splitting the target text based on a preset category.
[0066] Specifically, the preset category is the preset theme category involved in the application, such as preset categories like patents, software copyrights, and qualification certificates.
[0067] S402. Based on several first intermediate texts, a list of candidate texts corresponding to the candidate text is obtained, where the list of candidate texts includes several candidate texts, and the candidate text is the first intermediate text that meets the preset conditions obtained based on several second intermediate texts corresponding to the candidate text. The second intermediate text is the text obtained by splitting the candidate text based on a preset category.
[0068] Specifically, the preset condition is that the similarity between the category corresponding to the second intermediate text and the category corresponding to the first intermediate text is 1, where the category corresponding to the second intermediate text is one of the preset categories, and the category corresponding to the first intermediate text is one of the preset categories.
[0069] S403. Obtain the target application text list corresponding to the list of candidate texts to obtain the final application text, where the target application text list includes several target application texts, each candidate text corresponds to one target application text, and the final application text includes all the target application texts in the target application text list.
[0070] Specifically, S403 further includes the following steps:
[0071] S4031. Based on the candidate text, obtain the target title list set E = {E 1 , E 2 , E 3}, E 2 = {E 2 1 , ……, E 2 i , ……, E 2 n}, E 3 = {E 3 1 , ……, E 3 i , ……, E 3 n}, E 3 i = {E 3 i1 , ……, E 3 ij , ……, E 3 im(i)}, E 1 is the first target title, E 2 i is the i-th second target title in the second target title list E 1 corresponding to E 2 , and E 3 ij is the j-th third target title in the third target title list corresponding to E 2 i .
[0072] Specifically, the first target title is the first-level title in the candidate text.
[0073] Specifically, the second target title is the second-level title under the first-level title in the candidate text.
[0074] Specifically, the third target title is a third-level title under a second-level title in the text to be selected.
[0075] Furthermore, those skilled in the art are aware that any method for determining a title from a text in the prior art falls within the protection scope of the present invention, and will not be elaborated herein.
[0076] S4032. Obtain E according to the text to be selected 3 The corresponding specified condition text list set Q 3 ={Q 3 1 , ……, Q 3 i , ……, Q 3 n}, where Q 3 i ={Q 3 i1 , ……, Q 3 ij , ……, Q 3 im(i)}, where Q 3 ij is the specified condition text list corresponding to E 3 ij . The specified condition text list includes several specified condition texts, and the specified condition text is a conditional statement with a judgment nature obtained based on the text between two adjacent third target titles in the text to be selected.
[0077] Specifically, the specified condition text can be understood as follows: in a text to be selected, there will be text corresponding to the previous title between two adjacent third titles, and there will be some conditional statements in these texts. For example, if the number of patent applications in the mechanical field is 3 or more, it is recorded as 3 points, and if the number of patent applications in the mechanical field is less than 3, it is recorded as 1 point, and so on.
[0078] S4033. Obtain the corresponding specified priority list set J according to Q 3 . 3 The corresponding specified priority list set J 3 ={J 3 1 , ……, J 3 i , ……, J 3 n}, where J 3 i ={J 3 i1 , ……, J 3 ij , ……, J 3 im(i)}, where J3 ij For Q 3 ij The corresponding specified priority.
[0079] Specifically, the specified priority is the intermediate score obtained by comparing the first intermediate text corresponding to the text to be selected with the specified condition text in the specified condition text list, where the intermediate score is the total score of the third target title obtained by matching the first intermediate text corresponding to the text to be selected with the specified condition text included in Q 3 ij including the specified condition text.
[0080] S4034, according to J 3 , obtain the target application document corresponding to the text to be selected, where when J 3 ij ≠0, the text in the first intermediate text corresponding to the text to be selected that matches the text content under the third target title corresponding to J 3 ij is used as the target application text corresponding to the text to be selected.
[0081] As described above, according to whether the candidate object has a target requirement, the first processing method and the second processing method are respectively used to match the target text and the candidate text to obtain the final application text. Based on the different requirements of the candidate object, different matching methods are used for its result text to obtain the final application text, so that the accuracy of the obtained final application text is relatively high.
[0082] A system for obtaining a final application document provided in this embodiment, the system includes: a processor and a memory storing a computer program. When the computer program is executed by the processor, the following steps are implemented: obtaining a target text, obtaining a candidate text corresponding to a candidate object, when the candidate object has a target requirement, using the first processing method to compare the target text with the candidate text to obtain the final application text corresponding to the candidate object, and when the candidate object does not have a target requirement, using the second processing method to compare the target text with the candidate text to obtain the final application text corresponding to the candidate object; it can be seen that the present invention classifies policy texts, divides the classified policy texts into levels, and filters based on the requirements of the candidate object to determine the final application text, improving the efficiency of obtaining the final application text. Based on the different requirements of the candidate object, different matching methods are used for its result text to obtain the final application text, so that the accuracy of the obtained final application text is relatively high.
[0083] Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and not for limiting the scope of the present invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.
Claims
1. A system for obtaining a final application document, characterized in that: The system comprises: a processor and a memory storing a computer program, and when the computer program is executed by the processor, the following steps are implemented: S100, obtaining a target text, wherein the target text is a criterion text including a number of rules formulated to evaluate whether a target object satisfies a certain condition; S200, obtaining candidate texts corresponding to the candidate object, wherein the candidate object is an object to be matched with the target text to confirm whether it meets the corresponding requirements of the target text, and the candidate text is a text corresponding to a series of achievements possessed by the candidate object in a historical time period; S300, when there is a target requirement for the candidate object, a first processing method is used to compare the target text with the candidate text to obtain a final application text corresponding to the candidate object; S400: When there is no target requirement for the candidate object, a second processing method is used to compare the target text with the candidate text to obtain a final application text corresponding to the candidate object.
2. The system for obtaining the final application text according to claim 1, characterized in that: The candidate object is an object to be matched with the target text to confirm whether it meets the corresponding requirements of the target text.
3. The system for obtaining the final application text according to claim 1, characterized in that: The target requirement is a target score corresponding to the candidate object, wherein the target score is the score that the candidate object wants to confirm for matching the target text.
4. The system for obtaining the final application text according to claim 1, characterized in that: In S300, the final application text is obtained through the following steps: S301, based on the target text, obtaining a plurality of first intermediate texts, wherein the first intermediate texts are texts obtained by splitting the target text based on preset categories; S302, based on the plurality of first intermediate texts, obtaining a list of to-be-selected texts corresponding to the candidate texts, wherein the list of to-be-selected texts includes the plurality of to-be-selected texts, the to-be-selected texts being first intermediate texts that meet preset conditions and are obtained based on the plurality of second intermediate texts corresponding to the candidate texts, the second intermediate texts being texts obtained by splitting the candidate texts based on preset categories; S303, obtaining a target application text list corresponding to the to-be-selected text list to obtain the target application text, wherein the target application text list includes a plurality of target application texts, each to-be-selected text corresponds to a target application text, and the target application text includes all target application texts in the target application text list.
5. The system for obtaining the final application text according to claim 4, characterized in that: S303 also includes the following steps: S1, based on the selected text, obtain the target title list set E = {E 1 , E 2 , E 3 }, E 2 ={E 2 1, ..., E 2 i ,……,E 2 n }, E 3 ={E 3 1, ..., E 3 i ,……,E 3 n }, E 3 i ={E 3 i1 ,……,E 3 ij ,……,E 3 im(i) }, E 1 For the first target title, E 2 i For E 1 Corresponding second target title list E 2 The i-th second target title in E 3 ij For E 2 i The jth third target title in the corresponding third target title list; S2, according to E and the second intermediate text corresponding to the selected text, obtain the target priority list set F = {F1, ..., F i , ..., F n }, F i ={F i1 , ..., F ij , ..., F im(i) }, F ij For E 3 ij The target priority of the corresponding candidate path; S3, according to the text to be selected, obtain E 3 The corresponding specified condition text list set Q 3 = {Q 3 1, ..., Q 3 i , ..., Q 3 n }, Q 3 i = {Q 3 i1 , ..., Q 3 ij , ..., Q 3 im(i) }, Q 3 ij For E 3 ij A corresponding specified condition text list, wherein the specified condition text list includes a plurality of specified condition texts, and the specified condition texts are conditional statements with judgment properties obtained based on the text between two adjacent third target titles in the selected text; S4, according to specific target needs and Q 3 , obtain the target application text corresponding to the selected text, wherein the second intermediate text corresponding to the selected text is sequentially compared with Q in the target order 3 The target application text is determined by comparing the specified condition text list in the target text list with the target text list, obtaining the intermediate scores in turn until the sum of the intermediate scores obtained is not less than the target score, wherein the target order is the order in which the target priorities in F are sorted from large to small, and the intermediate score is the difference between the second intermediate text corresponding to the candidate text and Q. 3 ij The total score corresponding to the third target title is obtained by matching the specified conditional text.
6. The system for obtaining the final application text according to claim 1, characterized in that: In S400, the target application text is obtained through the following steps: S401, based on the target text, obtaining a plurality of first intermediate texts, wherein the first intermediate texts are texts obtained by splitting the target text based on preset categories; S402, based on the plurality of first intermediate texts, obtaining a list of to-be-selected texts corresponding to the candidate texts, wherein the list of to-be-selected texts includes the plurality of to-be-selected texts, the to-be-selected texts being first intermediate texts satisfying preset conditions obtained based on the plurality of second intermediate texts corresponding to the candidate texts, the second intermediate texts being texts obtained by splitting the candidate texts based on preset categories; S403, obtaining a target application text list corresponding to the list of to-be-selected texts to obtain a final application text, wherein the list of target application texts includes a plurality of target application texts, each to-be-selected text corresponds to a target application text, and the final application text includes all target application texts in the list of target application texts, wherein S403 also includes the following steps: S4031, based on the text to be selected, obtain the target title list set E = {E 1 , E 2 , E 3 }, E 2 ={E 2 1, ..., E 2 i ,……,E 2 n }, E 3 ={E 3 1, ..., E 3 i ,……,E 3 n }, E 3 i ={E 3 i1 ,……,E 3 ij ,……,E 3 im(i) }, E 1 For the first target title, E 2 i For E 1 Corresponding second target title list E 2 The i-th second target title in E 3 ij For E 2 i The jth third target title in the corresponding third target title list; S4032, according to the text to be selected, obtain E 3 The corresponding specified condition text list set Q 3 = {Q 3 1, ..., Q 3 i , ..., Q 3 n }, Q 3 i = {Q 3 i1 , ..., Q 3 ij , ..., Q 3 im(i) }, Q 3 ij For E 3 ij A corresponding specified condition text list, wherein the specified condition text list includes a plurality of specified condition texts, and the specified condition texts are conditional statements with judgment properties obtained based on the text between two adjacent third target titles in the selected text; S4033, according to Q 3 , get Q 3 The corresponding specified priority list set J 3 ={J 3 1, ..., J 3 i , ..., J 3 n }, J 3 i ={J 3 i1 , ..., J 3 ij , ..., J 3 im(i) }, J 3 ij Q 3 ij The corresponding specified priority; S4034, according to J 3 , obtain the target application file corresponding to the selected text, where J 3 ij ≠0, the first intermediate text corresponding to the selected text and J 3 ij The text that matches the text content under the corresponding third target title is used as the target application text corresponding to the selected text.
7. The system for obtaining the final application text according to claim 6, characterized in that: The designated priority is an intermediate score obtained by comparing the first intermediate text corresponding to the to-be-selected text with the designated conditional text in the designated conditional text list.
8. The system for obtaining the final application text according to claim 7, characterized in that: The intermediate score is the sum of the first intermediate text corresponding to the selected text and Q 3 ij The total score corresponding to the third target title is obtained by matching the specified conditional text.