Method and device for optimizing error correction result of legal document

文档序号：1087392 发布日期：2020-10-20 浏览：10次中文

阅读说明：本技术 法律文书纠错结果的优化方法及装置 (Method and device for optimizing error correction result of legal document ) 是由陈怡然于 2019-04-04 设计创作，主要内容包括：本发明公开了一种法律文书纠错结果的优化方法及装置,当对法律文书进行纠错,生成并显示法律文书中每个错误点的修改提示后,针对每个错误点记录用户操作信息；从已记录的错误点中提取可优化项；对于所述可优化项,对用户操作信息进行统计,得到所述可优化项的反馈调节参数值；当反馈调节参数值符合优化处理条件时,根据反馈调节参数值对应的优化处理方法对相应的所述可优化项进行优化处理。本发明通过记录并统计对可优化项的用户操作信息,得到每个可优化项的反馈调节参数值,并当反馈调节参数值符合优化处理条件时对相应的可优化项进行优化处理,提高了系统对法律文书进行纠错的准确率。(The invention discloses a method and a device for optimizing a legal document error correction result, which are used for recording user operation information aiming at each error point after the legal document is corrected and a modification prompt of each error point in the legal document is generated and displayed; extracting an optimizable term from the recorded error points; for the optimizable item, counting user operation information to obtain a feedback adjustment parameter value of the optimizable item; and when the feedback adjusting parameter value meets the optimization processing condition, optimizing the corresponding optimizable item according to the optimization processing method corresponding to the feedback adjusting parameter value. According to the method and the system, the feedback adjusting parameter value of each optimizable item is obtained by recording and counting the user operation information of the optimizable item, and the corresponding optimizable item is optimized when the feedback adjusting parameter value meets the optimization processing condition, so that the accuracy of the system for correcting the legal documents is improved.)

1. A method for optimizing the error correction result of a legal document is characterized by comprising the following steps:

after the legal document is corrected and the modification prompt of each error point in the legal document is generated and displayed, recording user operation information aiming at each error point;

extracting an optimizable term from the recorded error points;

for the optimizable item, counting user operation information to obtain a feedback adjustment parameter value of the optimizable item;

and when the feedback adjusting parameter value meets the optimization processing condition, optimizing the corresponding optimizable item according to the optimization processing method corresponding to the feedback adjusting parameter value.

2. The method of claim 1, wherein extracting an optimizable term from the recorded error points comprises:

and extracting error points which accord with a preset type from the recorded error points to serve as an optimizable item.

3. The method of claim 1, wherein the user action comprises: ignoring the operation, performing a recovery operation after ignoring the operation, and performing a manual correction operation.

4. The method of claim 3, wherein the counting user operation information for the optimizable item to obtain a feedback adjustment parameter value of the optimizable item comprises:

and for the optimizable item, counting the neglected operation of the user to obtain the neglected operation times of the optimizable item, and taking the neglected operation times as the feedback adjustment parameter value of the corresponding optimizable item.

5. The method according to claim 4, wherein the feedback adjustment parameter value meets the optimization processing condition when the feedback adjustment parameter value is greater than a preset minimum value of the number of neglecting operations; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

calling a corresponding relation between a preset feedback adjustment parameter interval and an optimization processing method, determining an optimization processing method corresponding to a feedback adjustment parameter value according to the feedback adjustment parameter interval in which the feedback adjustment parameter value is located, and performing optimization processing on the corresponding optimizable item by using the optimization processing method, wherein the feedback adjustment parameter interval comprises a low-order parameter interval and a high-order parameter interval, the optimization processing method corresponding to the low-order parameter interval is alarm information for generating an error correction rule corresponding to the optimizable item, and the optimization processing method corresponding to the high-order parameter interval is to cancel error correction on the optimizable item.

6. The method according to claim 3, wherein when the feedback adjustment parameter value is the number of times of performing the recovery operation after the ignoring operation, and when the feedback adjustment parameter value is greater than the minimum number of times of performing the recovery operation after the presetting operation, the feedback adjustment parameter value meets the optimization processing condition; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

and generating alarm information of the error correction rule corresponding to the optimizable item corresponding to the feedback adjustment parameter value.

7. The method according to claim 3, wherein when the feedback adjustment parameter value is the number of manual corrections, the feedback adjustment parameter value meets the optimization processing condition when the feedback adjustment parameter value is greater than a preset minimum value of the number of manual corrections; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

and generating a manual correction log of the optimizable item corresponding to the feedback adjusting parameter value.

8. An apparatus for optimizing the results of legal document error correction, comprising:

the user operation recording unit is used for recording user operation information aiming at each error point after the legal document is corrected and the modification prompt of each error point in the legal document is generated and displayed;

an optimizable item extracting unit for extracting an optimizable item from the recorded error points;

the user operation statistical unit is used for counting user operation information of the optimizable item to obtain a feedback adjusting parameter value of the optimizable item;

and the optimization processing unit is used for optimizing the corresponding optimizable item according to the optimization processing method corresponding to the feedback adjusting parameter value when the feedback adjusting parameter value meets the optimization processing condition.

9. A storage medium characterized in that the storage medium includes a stored program,

wherein, when the program runs, the device of the storage medium is controlled to execute the optimization method of the legal document error correction result according to any one of claims 1-7.

10. A processor, for running a program,

wherein the program when running performs the method of optimizing the results of a legal document correction as set forth in any one of claims 1-7.

Technical Field

The invention relates to the technical field of computers, in particular to a method and a device for optimizing an error correction result of a legal document, a storage medium and a processor.

Background

The legal document error correction system is suitable for the daily work of legal personnel, which often involves the auditing treatment of legal documents, and in order to improve the auditing efficiency of the legal personnel on the legal documents.

The error correction principle of the legal document error correction system in the market at present is to correct the legal document according to the preset error correction rule, realize the wrongly written characters in the legal document and the wrongly recognized punctuation marks, and improve the efficiency of the legal document audited by the legal staff to a certain extent.

However, once the conventional legal document error correction system is put into use, the built-in error correction rules cannot be changed, if the error correction rules do not conform to the actual conditions, that is, if an error correction rule error occurs, the legal document error correction system cannot be continuously used to meet the actual requirements, and if the legal document error correction system is required to meet the actual requirements, the legal document error correction system needs to be redeveloped, so that the maintenance cost of the legal document error correction system is increased.

Disclosure of Invention

In view of the above, the present invention has been developed to provide a method, apparatus, storage medium, and processor for optimizing the results of legal document error correction that overcome, or at least partially solve, the above-mentioned problems.

In order to achieve the above purpose, the invention provides the following specific technical scheme:

a method for optimizing the error correction result of legal documents comprises the following steps:

extracting an optimizable term from the recorded error points;

for the optimizable item, counting user operation information to obtain a feedback adjustment parameter value of the optimizable item;

Optionally, the categories of the error points include: document format errors, wrongly written characters, punctuation and symbol errors, document writing expression errors, legal basis citation errors, litigant name errors, and legal document dimension loss errors, wherein the preset types include: wrongly written characters, punctuation and symbol errors, written expression errors of documents, citation errors of legal bases, names errors of litigants and dimension loss errors of legal documents.

Optionally, the extracting an optimizable term from the recorded error points includes:

and extracting error points which accord with a preset type from the recorded error points to serve as an optimizable item. Optionally, the user operation includes: ignoring the operation, performing a recovery operation after ignoring the operation, and performing a manual correction operation.

Optionally, for the optimizable item, counting user operation information to obtain a feedback adjustment parameter value of the optimizable item, includes:

Optionally, when the feedback adjustment parameter value is greater than the minimum value of the preset neglected operation times, the feedback adjustment parameter value meets the optimization processing condition; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

Optionally, when the feedback adjustment parameter value is the number of times of performing the recovery operation after the neglect operation, and when the feedback adjustment parameter value is greater than the minimum value of the number of times of performing the recovery operation after the preset neglect operation, the feedback adjustment parameter value meets the optimization processing condition; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

and generating alarm information of the error correction rule corresponding to the optimizable item corresponding to the feedback adjustment parameter value.

Optionally, when the feedback adjustment parameter value is the manual correction frequency, and when the feedback adjustment parameter value is greater than the preset minimum manual correction frequency, the feedback adjustment parameter value meets the optimization processing condition; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

and generating a manual correction log of the optimizable item corresponding to the feedback adjusting parameter value.

An apparatus for optimizing the results of legal document error correction, comprising:

an optimizable item extracting unit for extracting an optimizable item from the recorded error points;

the user operation statistical unit is used for counting user operation information of the optimizable item to obtain a feedback adjusting parameter value of the optimizable item;

Optionally, the optimizable item extracting unit is specifically configured to extract an error point that meets a preset type from the recorded error points, as an optimizable item.

Optionally, the user operation includes: ignoring the operation, performing a recovery operation after ignoring the operation, and performing a manual correction operation.

Optionally, the user operation counting unit is specifically configured to count the neglected operations of the user for the optimizable item, to obtain the number of times of the neglected operations of the optimizable item, and use the number of times of the neglected operations as the feedback adjustment parameter value of the corresponding optimizable item.

Optionally, when the feedback adjustment parameter value is greater than the minimum value of the preset neglected operation times, the feedback adjustment parameter value meets the optimization processing condition; the optimization processing unit is specifically configured to invoke a corresponding relationship between a preset feedback adjustment parameter interval and an optimization processing method, determine an optimization processing method corresponding to a feedback adjustment parameter value according to the feedback adjustment parameter interval in which the feedback adjustment parameter value is located, and perform optimization processing on the corresponding optimizable item by using the optimization processing method, where the feedback adjustment parameter interval includes a low-order parameter interval and a high-order parameter interval, the optimization processing method corresponding to the low-order parameter interval is alarm information for generating an error correction rule corresponding to the optimizable item, and the optimization processing method corresponding to the high-order parameter interval is to cancel error correction on the optimizable item.

Optionally, when the feedback adjustment parameter value is the number of times of performing the recovery operation after the neglect operation, and when the feedback adjustment parameter value is greater than the minimum value of the number of times of performing the recovery operation after the preset neglect operation, the feedback adjustment parameter value meets the optimization processing condition; the optimization processing unit is specifically configured to generate alarm information of an error correction rule corresponding to the optimizable item corresponding to the feedback adjustment parameter value.

Optionally, when the feedback adjustment parameter value is the manual correction frequency, and when the feedback adjustment parameter value is greater than the preset minimum manual correction frequency, the feedback adjustment parameter value meets the optimization processing condition; the optimization processing unit is specifically configured to generate a manual correction log of the optimizable item corresponding to the feedback adjustment parameter value.

A storage medium including a stored program,

wherein, when the program runs, the device of the storage medium is controlled to execute the optimization method of the legal document error correction result.

A processor for running a program,

wherein the program executes the method for optimizing the error correction result of the legal document when running.

By means of the technical scheme, the method and the device for optimizing the error correction result of the legal document provided by the invention have the advantages that after the legal document is subjected to error correction, and the modification prompt of each error point in the legal document is generated and displayed, the user operation information of each error point is recorded, the optimizable item is extracted from the recorded error points, the user operation information of the optimizable item is recorded and counted, the feedback adjusting parameter value of the optimizable item is obtained, the corresponding optimizable item is subjected to optimization processing when the feedback adjusting parameter value meets the optimization processing condition, so that the legal document error correction system is more complete, the problem that the legal document error correction system needs to be redeveloped when the legal document error correction system does not meet the actual requirement is solved, and the accuracy of the system for correcting the legal document is improved.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 is a flow chart of a method for optimizing the error correction result of a legal document according to an embodiment of the present invention;

fig. 2 shows a schematic structural diagram of an optimizing apparatus for error correction results of legal documents according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The embodiment discloses an optimization method of a legal document error correction result, which is used for optimizing the error correction result of a legal document by a legal document error correction system, wherein a legal document specification library is respectively constructed for each type of the legal document in the legal document error correction system, so that the error correction is more targeted, and the error correction accuracy is higher. For example, the litigation-law document and the non-litigation-law document have different format specifications, and the litigation-law document format specification library is called when the error point of the litigation-law document is identified, and the non-litigation-law document format specification library is called when the error point of the non-litigation-law document is identified. And when the legal documents are corrected, calling the corresponding legal document specification library according to the types of the legal documents to correct the errors.

Referring to fig. 1, the method for optimizing the error correction result of the legal document disclosed in this embodiment specifically includes the following steps:

s101: after the legal document is corrected and the modification prompt of each error point in the legal document is generated and displayed, recording user operation information aiming at each error point;

it should be noted that the result of correcting the legal document includes: there is an error point in the legal document and no error point in the legal document.

When there are error points in the legal document, the number of error points may be one or more than one.

The categories of error points include: document format errors, wrongly written or mispronounced characters, punctuation and symbol errors, document writing expression errors, legal basis citation errors, litigant name errors, and legal document dimension loss errors.

The document format includes document paragraph separation, font style, font size, character spacing, line spacing, paragraph indentation, character position, paragraph special format, page margin, page number, page paging, etc. And calling a legal document format specification library, and identifying document format errors in the legal document to be processed according to a format specification corresponding to the type of the legal document to be processed in the format specification library.

And calling a preset wrongly written character error correction system to identify wrongly written characters in the legal documents.

The legal document error correction system identifies characters, punctuation marks, serial numbers and the like in the legal document by inspecting the intelligent analysis technology of the legal document, and compares and checks the problems of text broken lines, punctuation marks, grammar errors and the like in the document according to the information of the characters, the punctuation marks, the serial numbers and the like obtained after identification and the use rules of the broken lines and the punctuation marks to obtain punctuation and symbol errors.

And calling a legal document specification expression rule base, and identifying document writing expression errors in the legal document according to legal name writing rules, digital writing application rules of clauses and terms of the law, and falling date writing rules in the legal document specification expression rule base.

And calling the law rule base, and identifying the law in the legal document according to the citation error according to the intelligent analysis technology, the law name and the law original text in the law rule base.

Identifying the litigation positions of all the personnel in the legal document, establishing the association relationship between the name of each personnel and the litigation positions, and identifying the name error of the litigation personnel in the legal document according to the association relationship.

For dimension missing errors of legal documents, verifying key information items such as identity numbers and addresses in key information items in the legal documents, such as crime suspects, and key information items of each section of investigation authorities, criminal names and the like in an examination process section to judge whether all the key information items exist, and if not, performing error correction recommendation on corresponding field information extracted from a uniform service application system of the inspection authorities.

And after the legal document error correction system finishes error correction on the legal document, marking each error point in the legal document, and generating and displaying a modification prompt of each error point. Specifically, in the legal document, the identified error points are marked in a manner of highlighting, underlining, error display or the like, a correct expression corresponding to each error point is generated according to a legal document specification library, and the correct expression of each error point is displayed in the legal document.

When a user sees a modification prompt of error points in a legal document, the user can execute one-key modification operation for each error point, and modify the error points according to the modification prompt; the user can also execute the neglect operation and cancel the marking and modification prompt of the error point; the user can also perform recovery operation after executing the neglect operation, and recover the labeling and modification prompt of the error point; the user may also perform manual revision operations to delete portions of text or add portions of text in the legal instrument.

Thus, for each error point, the user operation comprises: ignoring the operation, performing a recovery operation after ignoring the operation, and performing a manual correction operation.

S102: extracting an optimizable term from the recorded error points;

there are various ways to extract the optimizable item from the recorded error points, one of which is to take all the recorded error points as optimizable items, and in this way to extract the optimizable item, as long as there are error points in the legal document, the optimizable item will be extracted.

In order to improve the optimization effect of the legal document error correction result, error points which are in accordance with a preset type can be extracted from the recorded error points to serve as an optimizable item. The preset types include: wrongly written characters, punctuation and symbol errors, written expression errors of documents, citation errors of legal bases, names errors of litigants and dimension loss errors of legal documents. It should be noted that, in this way of extracting the optimizable item, only the error point that matches the preset type may be used as the optimizable item, and therefore, the number of the optimizable items may be 0, 1, or more than one.

S103: for the optimizable item, counting user operation information to obtain a feedback adjustment parameter value of the optimizable item;

specifically, for each optimizable item, classification statistics is performed on user operation information, that is, the times of ignoring operation, the times of performing recovery operation after ignoring operation, and the times of manual correction operation of the same optimizable item are respectively counted.

Correspondingly, for the same optimizable item, the feedback adjustment parameter value comprises the times of neglecting operation, the times of carrying out recovery operation after neglecting operation and the times of manual correction operation.

S104: and when the feedback adjusting parameter value meets the optimization processing condition, optimizing the corresponding optimizable item according to the optimization processing method corresponding to the feedback adjusting parameter value.

And when the feedback adjusting parameter value is the neglecting operation times, and the feedback adjusting parameter value is greater than the minimum value of the preset neglecting operation times, the feedback adjusting parameter value accords with the optimization processing condition.

Specifically, a preset corresponding relationship between a feedback adjustment parameter interval and an optimization processing method is called, an optimization processing method corresponding to the feedback adjustment parameter value is determined according to the feedback adjustment parameter interval in which the feedback adjustment parameter value is located, and the optimization processing method is used for performing optimization processing on the corresponding optimizable item, wherein the feedback adjustment parameter interval comprises a low-order parameter interval and a high-order parameter interval, the optimization processing method corresponding to the low-order parameter interval is alarm information for generating an error correction rule corresponding to the optimizable item, and the optimization processing method corresponding to the high-order parameter interval is used for cancelling error correction on the optimizable item.

If the low-order parameter interval is [10,30], the high-order parameter interval is [31, + ∞ ], if the optimizable item is that the person for defending is changed into the person for identification, when the operation times are ignored within the low-order parameter interval, alarm information of the error correction rule (the person for defending is changed into the person for identification) is generated, manual audit analysis and processing optimization are synchronously performed on the rule maintainer, the optimized text error correction rule is updated to the text error correction system, a new error correction rule is executed on a legal text newly entering the text error correction system, and when the person for defending is identified, error point marking is not performed any more; when the neglected operation times are in a high-order parameter interval, the error correction of the optimizable item (changing the dialer into the identifier) is cancelled, and the alarm information of the error correction rule (changing the dialer into the identifier) is generated under the condition of need and is synchronized to the rule maintainer.

And when the feedback adjusting parameter value is the number of times of the recovery operation after the neglect operation, and when the feedback adjusting parameter value is larger than the preset minimum number of times of the recovery operation after the neglect operation, the feedback adjusting parameter value accords with the optimization processing condition, alarm information of the error correction rule corresponding to the optimizable item corresponding to the feedback adjusting parameter value is generated, manual audit analysis and processing optimization are synchronously performed on the alarm information, rule maintenance personnel are synchronously performed, the optimized document error correction rule is updated to the document error correction system, and a new error correction rule is executed on a legal document newly entering the document error correction system.

And when the feedback adjusting parameter value is the manual correction frequency, and when the feedback adjusting parameter value is larger than the preset minimum manual correction frequency, the feedback adjusting parameter value accords with the optimization processing condition, and a manual correction log of the optimizable item corresponding to the feedback adjusting parameter value is generated, so that a super manager, such as a product designer, can call the manual correction log at any time, and data support and basis are provided for the product designer to track the usability and thinking optimizability of the product.

Based on the method for optimizing the error correction result of the legal document disclosed in the above embodiment, the embodiment correspondingly discloses an apparatus for optimizing the error correction result of the legal document, please refer to fig. 2, and the apparatus specifically includes:

a user operation recording unit 201, configured to record user operation information for each error point after the legal document is corrected, and a modification prompt for each error point in the legal document is generated and displayed;

optionally, the categories of the error points include: document format errors, wrongly written characters, punctuation and symbol errors, document writing expression errors, legal basis citation errors, litigant name errors, and legal document dimension loss errors, wherein the preset types include: wrongly written characters, punctuation and symbol errors, written expression errors of documents, citation errors of legal bases, names errors of litigants and dimension loss errors of legal documents.

Optionally, the user operation includes: ignoring the operation, performing a recovery operation after ignoring the operation, and performing a manual correction operation.

An optimizable item extraction unit 202 for extracting an optimizable item from the recorded error points;

optionally, the optimizable item extracting unit 202 is specifically configured to extract an error point that meets a preset type from the recorded error points, as an optimizable item.

A user operation counting unit 203, configured to count user operation information for the optimizable item to obtain a feedback adjustment parameter value of the optimizable item;

and the optimization processing unit 204 is configured to, when the feedback adjustment parameter value meets the optimization processing condition, perform optimization processing on the corresponding optimizable item according to an optimization processing method corresponding to the feedback adjustment parameter value.

Optionally, the user operation counting unit 203 is specifically configured to count the neglected operations of the user for the optimizable item, to obtain the number of times of the neglected operations of the optimizable item, and use the number of times of the neglected operations as a feedback adjustment parameter value of the corresponding optimizable item.

Optionally, when the feedback adjustment parameter value is greater than the minimum value of the preset neglected operation times, the feedback adjustment parameter value meets the optimization processing condition; the optimization processing unit 204 is specifically configured to invoke a corresponding relationship between a preset feedback adjustment parameter interval and an optimization processing method, determine an optimization processing method corresponding to a feedback adjustment parameter value according to the feedback adjustment parameter interval in which the feedback adjustment parameter value is located, and perform optimization processing on the corresponding optimizable item by using the optimization processing method, where the feedback adjustment parameter interval includes a low-order parameter interval and a high-order parameter interval, the optimization processing method corresponding to the low-order parameter interval is alarm information for generating an error correction rule corresponding to the optimizable item, and the optimization processing method corresponding to the high-order parameter interval is to cancel error correction on the optimizable item.

Optionally, when the feedback adjustment parameter value is the number of times of performing the recovery operation after the neglect operation, and when the feedback adjustment parameter value is greater than the minimum value of the number of times of performing the recovery operation after the preset neglect operation, the feedback adjustment parameter value meets the optimization processing condition; the optimization processing unit 204 is specifically configured to generate alarm information of an error correction rule corresponding to the optimizable item corresponding to the feedback adjustment parameter value.

Optionally, when the feedback adjustment parameter value is the manual correction frequency, and when the feedback adjustment parameter value is greater than the preset minimum manual correction frequency, the feedback adjustment parameter value meets the optimization processing condition; the optimization processing unit 204 is specifically configured to generate a manual correction log of the optimizable item corresponding to the feedback adjustment parameter value.

The device for optimizing the error correction result of the legal document disclosed by the embodiment records the user operation information of each error point, extracts the optimizable item from the recorded error points, records and counts the user operation information of the optimizable item to obtain the feedback adjusting parameter value of each optimizable item after the legal document is subjected to error correction and a modification prompt of each error point in the legal document is generated and displayed, and performs optimization processing on the corresponding optimizable item when the feedback adjusting parameter value meets the optimization processing condition, so that the legal document error correction system is more perfect, the problem that the legal document error correction system needs to be redeveloped when the legal document error correction system does not meet the actual requirement is solved, and the accuracy of the system for correcting the legal document is improved.

The device for optimizing the error correction result of the legal document comprises a processor and a memory, wherein the user operation recording unit, the optimizable item extracting unit, the user operation counting unit, the optimizing processing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more than one kernel can be set, and the error correction accuracy is improved by adjusting kernel parameters.

The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

An embodiment of the present invention provides a storage medium, on which a program is stored, which, when executed by a processor, implements the method for optimizing the error correction result of a legal document.

The embodiment of the invention provides a processor, which is used for running a program, wherein the method for optimizing the error correction result of the legal document is executed when the program runs.

The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps:

extracting an optimizable term from the recorded error points;

for the optimizable item, counting user operation information to obtain a feedback adjustment parameter value of the optimizable item;

Further, the categories of the error points include: document format errors, wrongly written characters, punctuation and symbol errors, document writing expression errors, legal basis citation errors, litigant name errors, and legal document dimension loss errors, wherein the preset types include: wrongly written characters, punctuation and symbol errors, written expression errors of documents, citation errors of legal bases, names errors of litigants and dimension loss errors of legal documents.

Further, the user operation includes: ignoring the operation, performing a recovery operation after ignoring the operation, and performing a manual correction operation.

Further, the extracting the optimizable item from the recorded error points includes:

and extracting error points which accord with a preset type from the recorded error points to serve as an optimizable item.

Further, for the optimizable item, counting user operation information to obtain a feedback adjustment parameter value of the optimizable item, including:

Further, when the feedback adjusting parameter value is larger than the minimum value of the preset neglected operation times, the feedback adjusting parameter value accords with the optimization processing condition; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

Further, when the feedback adjusting parameter value is the number of times of performing the recovery operation after the neglect operation, and when the feedback adjusting parameter value is larger than the minimum value of the number of times of performing the recovery operation after the preset neglect operation, the feedback adjusting parameter value meets the optimization processing condition; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

and generating alarm information of the error correction rule corresponding to the optimizable item corresponding to the feedback adjustment parameter value.

Further, when the feedback adjusting parameter value is the manual correction times, and when the feedback adjusting parameter value is larger than the preset minimum value of the manual correction times, the feedback adjusting parameter value meets the optimization processing condition; the optimizing process is performed on the corresponding optimizable item according to the optimizing process method corresponding to the feedback adjusting parameter value, and the optimizing process comprises the following steps:

and generating a manual correction log of the optimizable item corresponding to the feedback adjusting parameter value.

The device herein may be a server, a PC, a PAD, a mobile phone, etc.

The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: