CN111292068B

CN111292068B - Contract information auditing method and device, electronic equipment and storage medium

Info

Publication number: CN111292068B
Application number: CN202010133899.XA
Authority: CN
Inventors: 任宁
Original assignee: Dingfu Intelligent Technology Co ltd
Current assignee: Dingfu Intelligent Technology Co ltd
Priority date: 2020-02-28
Filing date: 2020-02-28
Publication date: 2024-02-09
Anticipated expiration: 2040-02-28
Also published as: CN111292068A

Abstract

The application provides a contract information auditing method, a contract information auditing device, electronic equipment and a storage medium. The method comprises the following steps: acquiring contract information, and extracting information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information; and for each piece of key information, auditing the key information by using a corresponding auditing model to obtain an auditing result. According to the embodiment of the application, the contract information is automatically extracted, and each piece of extracted key information is automatically audited, so that manual participation is not needed, human resources are saved, and auditing efficiency and accuracy are improved.

Description

Contract information auditing method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method and apparatus for auditing contract information, an electronic device, and a storage medium.

Background

A contract is an agreement between parties or between parties to set up, alter, and terminate civil relationships. From a legal point of view, all market trade actions are contractual actions. In enterprises, the importance of contracts goes without saying that in life, contracts are more or less relevant to everyone. The contract auditing is to audit the factors such as normalization and consistency of the contract, whether the definition of the contract property is reasonable, whether the main body is qualified and the like.

Contract auditing is an important task in large and medium enterprises, is usually performed manually, and is relatively low in accuracy rate in the face of a large amount of contract contents.

Disclosure of Invention

An embodiment of the application aims to provide a contract information auditing method, device, electronic equipment and storage medium, which are used for improving auditing efficiency and accuracy.

In a first aspect, an embodiment of the present application provides a method for auditing contract information, including: acquiring contract information, and extracting information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information; and for each piece of key information, auditing the key information by using a corresponding auditing model to obtain an auditing result.

According to the embodiment of the application, the contract information is automatically extracted, and each piece of extracted key information is automatically audited, so that manual participation is not needed, human resources are saved, and auditing efficiency and accuracy are improved.

Further, the auditing the key information by using the corresponding auditing model to obtain an auditing result includes: extracting a suspected capitalization amount from the at least one key information through a first regular expression; performing numerical conversion on the suspected capitalized amount; if no conversion result exists, determining that the suspected capitalized amount is not standard; if the conversion result is obtained, matching the suspected capitalization amount with a second regular expression, wherein the second regular expression comprises a plurality of sub-expressions for auditing the nonstandard description; and if the suspected capitalization amount is successfully matched with any one of the sub-expressions, determining that the suspected capitalization amount is not standard.

Because the capitalized amount may be written in the contract information, whether the capitalized amount in the contract information is wrong or not can be accurately identified by auditing the capitalized amount in the contract information through the first regular expression and the second regular expression.

Further, the auditing the key information by using the corresponding auditing model to obtain an auditing result includes: extracting the suspected composite unit lower case amount from the at least one key information through a third regular expression; matching the suspected composite unit lower case amount by using a fourth regular expression; if the matching is successful, determining that the suspected composite unit lower case amount is wrong; if the matching is unsuccessful, extracting a character string from the suspected composite unit lower case amount to obtain a first composite unit lower case amount; wherein the character string includes a number; performing numerical conversion on the suspected composite unit lower case amount to obtain a second composite unit lower case amount; and if the lower case amount of the first composite unit is consistent with the lower case amount of the second composite unit, the lower case amount of the suspected composite unit is standard, otherwise, the lower case amount of the suspected composite unit is not standard.

According to the embodiment of the application, the composite unit lower case amount in the contract information is audited through the third regular expression and the fourth regular expression, so that whether the composite unit lower case amount in the contract information is wrong or not can be accurately identified.

Further, the time information includes a contract period start time, a contract period end time, a contract period start time, and a contract period end time; the step of auditing the key information by using the corresponding auditing model to obtain auditing results comprises the following steps: normalizing the contract period starting time, the contract period ending time, the contract period starting time and the contract period ending time; wherein, the contract period refers to a contract period specified by the contract and not to be revocable; contract time periods refer to respective time periods in the contract period; sequencing the starting time and the ending time of the contract time period according to time sequence; determining that the contract information is not canonical if any of the following is satisfied: the first contract period starting time is different from the contract period starting time; the last contract period end time is different from the contract period end time; in the two adjacent contract periods, the ending time of the previous contract period is not the day before the starting time of the next contract period.

For the contract, the situation that the whole contract period is not matched with each contract time period may occur, so that the embodiment of the application realizes the accurate auditing of the contract period and the contract time period through the preset condition, and prevents the problem that the date of the contract period is not corresponding to the date of each contract time period.

Further, the auditing the key information by using the corresponding auditing model to obtain an auditing result includes: acquiring a plurality of amount information in the same contract time period from at least one piece of key information, wherein each amount information comprises an original currency value, a time type, an area type and a tax-containing type; comparing the time type, the area type and the tax-containing type in the amount information to determine different types; normalizing the original coin values of different types to obtain the original coin value of the same type; and comparing the original currency values of the plurality of amount information under the same type, and if the original currency values are different, determining that the contract information is not standard.

According to the method and the device, the original coin values of different types are normalized to the original coin values of the same type, so that whether the lease amount conversion in the audit information is consistent is judged.

Further, the key information also comprises amount change information, wherein the amount information comprises a basic amount and a changed amount; the step of auditing the key information by using the corresponding auditing model to obtain auditing results comprises the following steps: calculating according to the basic amount and the amount change information to obtain an estimated changed amount; and comparing the predicted changed amount with the changed amount, and if the predicted changed amount is inconsistent with the changed amount, determining that the contract information is not standard.

According to the method and the device, whether the changed money in the same information is correct or not is checked through the basic money and the money change information, and calculation errors of the changed money are prevented.

Further, the extracting the information of the contract information to obtain at least one key information in the contract information includes: and extracting information from each row of the contract information by using a fifth regular expression to obtain at least one piece of key information in the contract information.

The embodiment of the application accurately extracts the key information from the contract information through the fifth regular expression.

In a second aspect, an embodiment of the present application provides a contract information auditing apparatus, including: the information extraction module is used for acquiring contract information, extracting information from the contract information and acquiring at least one key information in the contract information; wherein the key information comprises amount information and time information; and the information auditing module is used for auditing the key information by utilizing the corresponding auditing model aiming at each key information to obtain an auditing result.

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory, and a bus, wherein,

The processor and the memory complete communication with each other through the bus;

the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of the first aspect.

In a fourth aspect, embodiments of the present application provide a non-transitory computer readable storage medium comprising:

the non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the method of the first aspect.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a contract information auditing method according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of an auditing apparatus according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

Fig. 1 is a schematic flow chart of a contract information auditing method provided in an embodiment of the present application, as shown in fig. 1, a main body for executing the method is an auditing device, and the auditing device may be a desktop computer, a notebook computer, a tablet computer, a smart phone, an intelligent wearable electronic device, a server, and the like. The method comprises the following steps:

step 101: acquiring contract information, and extracting information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information;

step 102: and for each piece of key information, auditing the key information by using a corresponding auditing model to obtain an auditing result.

In step 101, the contract information is a contract of an electronic version, and if the contract information is a paper contract, the paper version can be converted into the electronic version by an optical character recognition OCR technology. Wherein, the optical character recognition refers to a process that an electronic device (such as a scanner or a digital camera) checks characters printed on paper, determines the shape thereof by detecting dark and bright modes, and then translates the shape into computer characters by a character recognition method; that is, the technology of converting the characters in the paper document into the image file of black-white lattice by optical mode and converting the characters in the image into the text format by the recognition software for further editing and processing by the word processing software is adopted. It will be appreciated that the contract information for the paper version may also be converted to the electronic version by other techniques.

Because of more characters in the contract information, in order to improve the auditing efficiency, the contract information is extracted, so that key information contained in the contract information is obtained. It will be appreciated that different types of contract information include different key information. For example: for the rental contract, the key information may be amount information and time information, and the amount information includes monthly rent, yearly rent, and the like; the time information includes a rental period, each of the rental periods, and the like. For a sales contract, the key information can be tax-containing list price, commodity quantity, total price and the like. The information extraction method in the specific and the same information is described in the following embodiments.

In step 102, after the auditing apparatus extracts the key information in the contract information, each key information is audited. It should be noted that, the auditing models used by different key information are different, so that the key information is audited by selecting the corresponding auditing model. And if the key information is checked and found to be out of specification, an alarm prompt can be given.

On the basis of the above embodiment, the extracting the information of the contract information to obtain at least one key information in the contract information includes:

and extracting information from each row of the contract information by using a fifth regular expression to obtain at least one piece of key information in the contract information.

In a specific implementation process, a fifth regular expression may be generated in advance, and it may be understood that different types of contract information may use different fifth regular expressions, and of course, the fifth regular expressions corresponding to different types of contract information may also be fused into one.

When the information extraction is carried out on the same information, the same information is segmented, and the line changing symbol can be used as a segmentation point for segmentation. Information extraction is then performed on each row using the fifth regular expression.

Assume that the contract information includes "first-year rent: from month 02 of 2018 to month 02 of 2019 15, contains tax lease 228000 (uppercase: two-ten thousands of baqian, two-ten thousand baqian, ten six five years: from month 02 of 2019 16 to month 02 of 2023 15, each year contains tax lease 248720 (uppercase: two-ten-six-four-eight Qian Qi Bai Er Yuan Ji) ". It can be seen from the corpus above that the amount information is not an isolated value, but a series of information including:

The amount type (including rent, property fee, water fee, deposit, etc.), currency, raw currency value, uppercase amount, lowercase amount, tax, corresponding tax type, rent time type (annual rent, monthly rent, daily rent), rent area type (square meter rent), rent corresponding lease (start time, end time).

The content that can be analyzed from the corpus above is:

1. type of amount: renting; original monetary value: 228000.00; capitalized amount: two-ten thousand baqin yuan; lower case amount: 228000 yuan; whether contain tax: is; rent corresponds to the beginning time of the lease: 2 months and 16 days 2018; rent corresponds to the end time of the lease: 02 and 15 days 2019.

2. Type of amount: renting; original monetary value: 248720.00; capitalized amount: two-ten thousand eight Qian seven Bai Yuan; lower case amount: 248720 yuan; whether contain tax: is; rent corresponds to the beginning time of the lease: 2 months 16 days 2019; rent corresponds to the end time of the lease: 2023, 2, 15; rent time type: and renting the money in a year.

Each fifth regular expression may be described by the form of the following table. In the following table, the first column represents a first class corresponding to the fifth regular expression and can be understood as a large class, the second column represents a class corresponding to the fifth regular expression, namely a specific class below the first class, the third column is a specific fifth regular expression, and the fourth column is a unit corresponding to content selected by the fifth regular expression. It will be appreciated that the regular expressions listed in the following vocabulary are just one example, and that the corresponding regular expressions may be written according to actual situations:

After information extraction is performed on the corpus through the word list, the following output result can be obtained:

it should be noted that if a long string and a short string are matched at the same time, it is understood that the long string and the short string are relatively speaking, the long string means a longer character string, and the short string means a shorter character string. If two strings, namely a first string and a second string, are matched, if the starting position of the first string is smaller than or equal to the starting position of the second string, the ending position of the first string is larger than or equal to the ending position of the second string, namely the first string contains the second string, the first string is a long string, and the second string is a short string, at this time, only the long string is output, and it should be noted that the situation that the starting position of the first string is not equal to the starting position of the first string and the ending position of the first string is equal to the ending position of the first string is not included here. For example, "second year to fifth year" is matched to both "second year to fifth year" and "second year", "fifth year". Only "the second year to the fifth year" is output.

In addition, when matching is performed, the lower case amount or the upper case amount may be used as an anchor point to correspond to the related information. The following takes the lower case amount as an anchor point as an example:

1) Positioning to the position of the lower case money;

2) The position of the lower case amount is located, and the text matched by the following expressions of several categories, which appear after the previous amount, is found forward to be closest to it:

the categories are: time unit, area unit, time sequence, specific time, electricity charge unit and weight unit; the name of the primary class is: a money name.

3) The location of the lower case amount finds the nearest text to it, matching the expressions of several categories that appear before the latter amount:

the categories are: time unit, area unit, electricity charge unit and weight unit; the name of the primary class is: a money name.

The requirements for the corresponding relevant information for steps 2) and 3) above are as follows:

the expressions of each category output matching text only once. For example, if a most recent category of information is found from the location of the amount forward, and this information appears after the previous amount, then no more backward is found.

Except for a specific time, the location to which the information expression associated with a certain amount matches to the text must appear after the previous amount and before the latter amount. For example, if a nearest one is found from the position of the amount forward, but this one appears before the previous amount, then a further backward search is required.

The analysis for a specific time is different from the analysis for other amount related information. A specific lease time describing the coverage of a certain amount may appear in a portion of the paragraph further forward as a lease time shared by several amounts. Such as: the lease of each month from 11.19 in 2021 to 18 in 2023 is Renminbi Yi Wanzhen Baijiu yuan zhi (114490 yuan). The property fee per month is Liu Moer kilo-dew (Liu She yuan) five-corner integer (62969.5 yuan).

The time corresponding to 114490 yuan of rentals and the time corresponding to 62969.5 yuan of property fees per month in the corpus are from 2021, 11, 19 days to 2023, 11, 18 days. This time should be taken as the corresponding specific time for the two amounts.

On the basis of the above embodiment, the auditing the key information by using the corresponding auditing model to obtain an auditing result includes:

extracting a suspected capitalization amount from the at least one key information through a first regular expression;

performing numerical conversion on the suspected capitalized amount;

if no conversion result exists, determining that the suspected capitalized amount is not standard;

If the conversion result is obtained, matching the suspected capitalization amount with a second regular expression, wherein the second regular expression comprises a plurality of sub-expressions for auditing the nonstandard description;

and if the suspected capitalization amount is successfully matched with any one of the sub-expressions, determining that the suspected capitalization amount is not standard.

In a specific implementation process, firstly, the auditing device uses the first regular expression to extract the suspected capitalized amount from the extracted key information, wherein the suspected capitalized amount refers to a key word which may be the capitalized amount in the contract information. Wherein, the first regular expression may be: hundred and ten million hundred thousand + [_4e00-_9fa5 {0,2} ([ two, three, five, seven, eight, ninety-zero ] Bai He Qian He Yi Bai Qian + [_4e00-_9fa5] {0,2} ([ two, three, four, six, seven, eight and ninety zero ] two ten and three ten Wu Liu bajia, one hundred million hundred thousand [_4e00-_9fa5] {0,2 }) {0, and (3) elements. It should be noted that the first regular expression may be preset according to actual situations, as long as a keyword suspected to be a capitalized amount can be extracted.

And carrying out numerical conversion on the suspected capitalized amount after the suspected capitalized amount is obtained, wherein conversion can be carried out by adopting a Microsoft numerical conversion tool, and if no result exists, determining that the suspected capitalized amount is not standard. It will be appreciated that multiple suspected capitalized amounts may be extracted from one piece of contract information, and therefore, each of the suspected capitalized amounts may need to be converted and then reviewed one by one.

And if the result is found, matching the suspected capitalized amount with the conversion result again by using the second regular expression. Wherein, the description of the second regular expression is as follows:

for example: if the suspected capitalized amount of the conversion result is matched with the second regular expression in the table, reporting that the capitalized amount is not standard: the complex simplified body is mixed with the alarm prompt.

Thus, the first regular expression is used for roughly auditing the suspected capitalized amount, filtering out some obvious non-compliance, and the second regular expression is used for auditing in detail and giving specific non-compliance reasons when the non-compliance is met.

According to the embodiment of the application, the capitalized amount in the contract information is audited through the first regular expression and the second regular expression, so that whether the capitalized amount in the contract information is wrong or not can be accurately identified.

extracting the suspected composite unit lower case amount from the at least one key information through a third regular expression;

matching the suspected composite unit lower case amount by using a fourth regular expression;

if the matching is successful, determining that the suspected composite unit lower case amount is wrong;

if the matching is unsuccessful, extracting a character string from the suspected composite unit lower case amount to obtain a first composite unit lower case amount; wherein the character string includes a number;

performing numerical conversion on the suspected composite unit lower case amount to obtain a second composite unit lower case amount;

and if the lower case amount of the first composite unit is consistent with the lower case amount of the second composite unit, the lower case amount of the suspected composite unit is standard, otherwise, the lower case amount of the suspected composite unit is not standard.

In a specific implementation, the contract information may include a plurality of composite unit lower case amounts, where a composite unit lower case amount refers to a combination of a lower case amount in an amount with other units. For example, in a lease contract, "85859.76 Yuan/month" and "Yuan/month" are compound units. After OCR or text encoding corpus recognition by optical character recognition, the corpus recognition can be identified as '85859,76 Yuan 7 month', numerical errors can be seen, and units are also in error. Therefore, the auditing device can extract the suspected compound unit lower case amount from the key information through the third regular expression. The third regular expression may be: [ \d ] [ d ]? ([ \d\s\, ]) 0,15} {0,2} [ month old ], but of course, other expressions capable of identifying the lower case amount of the suspected compound unit may be used, and the specific content of the third regular expression is not limited in the embodiment of the present application.

After the suspected composite unit lower case amount is obtained, matching the suspected composite unit lower case amount using a fourth regular expression, where the fourth regular expression may be: [, ] \d {0,2} element. If the small amount of the suspected composite unit is successfully matched with the fourth regular expression, the small amount of the suspected composite unit is not standard, and the alarm prompt is given.

If the matching is unsuccessful, extracting character strings consisting of all numbers, commas (commas) and dot numbers (number) from the suspected composite unit lower case amount according to the sequence of the characters in the text, and obtaining the first composite unit lower case amount. For example:

the contract information is: the lease is 12,000.00 yuan/month from 1 st 2012 to 30 th 2013, and the extracted first compound unit lower case amount is: 12,000.00, and then performing numerical conversion on the suspected composite unit lower case amount which is not successfully matched by using a conversion tool of microsoft to obtain a second composite unit lower case amount. It should be noted that other conversion tools may be used for conversion, and embodiments of the present application are not limited in detail. If the conversion fails, the suspected composite unit lower case amount is not normalized.

It should be noted that, for a small amount without a decimal number, there may be no comma or dot number in the corresponding small amount of the suspected composite unit, for example: the lease is 1200 yuan/month, and the first composite unit lower case amount extracted by the lease is: 1200.

If the conversion is successful, the first composite unit lower case amount is compared with the second composite unit lower case amount, if the first composite unit lower case amount and the second composite unit lower case amount are consistent, the suspected composite unit lower case amount is standard, and otherwise, the suspected composite unit lower case amount is not standard.

According to the embodiment of the application, the lower case amount in the contract information is audited through the third regular expression and the fourth regular expression, so that whether the lower case amount in the contract information is wrong or not can be accurately identified.

On the basis of the above embodiment, the time information includes a contract period start time, a contract period end time, a contract period start time, and a contract period end time; the step of auditing the key information by using the corresponding auditing model to obtain auditing results comprises the following steps:

normalizing the contract period starting time, the contract period ending time, the contract period starting time and the contract period ending time; wherein, the contract period refers to a contract period specified by the contract and not to be revocable; contract time periods refer to respective time periods in the contract period;

sequencing the starting time and the ending time of the contract time period according to time sequence;

Determining that the contract information is not canonical if any of the following is satisfied:

the first contract period starting time is different from the contract period starting time;

the last contract period end time is different from the contract period end time;

in the two adjacent contract periods, the ending time of the previous contract period is not the day before the starting time of the next contract period.

In a specific implementation, for a contract, the contract information may include information about the contract period and the contract time period. There may be situations where the contract period does not match the contract period, for example: the start of the contract period and the resulting time are not connected end to end, the collection of contract periods is inconsistent with the contract period, etc. Thus, auditing of the contract period and contract time period is required. In the contract information, some time information is specific year, month, and day, and some time information is not year, month, and day, and the rental contract is taken as an example: : the lease period is "2015, 11, 2, 10, 2018, 2, 10" and the third lease year "refers to" 2017, 2, 11, 10, 2018, 2, 10 ". Therefore, the third lease year needs to be normalized to get the corresponding year, month and day.

Wherein time normalization can be achieved by the expression in the following table:

it should be noted that $1 refers to the first parenthesis; and $2 refers to the content in the second bracket, and the content is converted into a numerical value after being taken out.

For example, the expression of the key information extracted from the contract information of the rental contract is: { 'price:' 1028572.55 yuan ',' title_price: 'one hundred thousand eight kilobars @ Wu two thousand eight basic bars }, type_of_fe:' lease }, unit_of_time: 'year }, sequence_of_time:' third lease year }.

The expression matching is performed on the sequence_of_time (time series) output in the amount information entry according to the above table. The time of the sequence is obtained as information of time period/time point, numerical value, time unit and the like. For the sequence time characterizing the time point, the specific time is directly analyzed according to the date of the rental start and end. The specific time is obtained by taking 3 in the value of the third lease year and then calculating on the basis of the date of lease start and end. For the sequence time characterizing the rental period, there are two cases:

1) The values in time represent the length of time. Such as "first three years", "last five years". The time length is obtained and the specific time is calculated.

2) The values in time represent the time start and end. Such as "first year to fifth year", "second year, third year". The values of the time start and end are obtained and the specific time is calculated.

After the normalization process is completed, the rental period start time and the rental period end time are ordered, for example: the lease period is as follows: from 1/6/2015 to 31/5; the lease time periods are respectively as follows: a first rental period [2015, 6, 1, to 2016, 5, 31 ] and a second rental period [2016, 6, 1, to 2017, 5, 31 ] are obtained after sorting: 2015, 6, 1, 2016, 5, 31, 2016, 6, 1, 2017, 5, 31.

The first rental period start time refers to the start time of the first rental period in the rental period, i.e., 2015, 6, 1, etc. is the first rental period start time. The 1 st of 2015, 6 th, is also the start time of the rental period.

And the ending time of the last lease time period is the ending time of the last lease time period in the lease period. I.e. 31 days 5 and 31 in 2017. The end time of the rental period is 2017, 5, 31 days.

If the lease period and the lease time period do not meet any one of the conditions, the contract information is not standard, and the alarm prompt is given.

According to the embodiment of the application, accurate auditing of the contract period and the contract time period is realized through the preset condition, and the problem that the contract period does not correspond to the date of each contract time period is prevented.

acquiring a plurality of amount information in the same contract time period from at least one piece of key information, wherein each amount information comprises an original currency value, a time type, an area type and a tax-containing type;

comparing the time type, the area type and the tax-containing type in the amount information to determine different types;

normalizing the original coin values of different types to obtain the original coin value of the same type;

and comparing the original currency values of the plurality of amount information under the same type, and if the original currency values are different, determining that the contract information is not standard.

In a specific implementation, take a lease contract as an example: the corresponding units may be different for the amounts in the contract information, for example: daily rentals, monthly rentals, annual rentals, rentals corresponding to total area, rentals corresponding to unit area, and the like. An audit of whether the lease amount conversion is consistent may include the following:

1) And in the same lease time period, whether the conversion of the lease amounts of different time types is consistent or not.

The time types of rentals refer to annual rentals, monthly rentals and daily rentals. If the daily rent is 100 yuan, the monthly rent should be 3000 yuan and the annual rent should be 36000 yuan.

2) And in the same lease time period, whether the lease amount conversion of different area types is consistent or not, namely, whether the lease amount and area in square meter are consistent or not with the lease amount conversion or not.

The house area is as follows: 200 square meters, the monthly rent is 20000 yuan, and every square meter of monthly rent should be 100 yuan.

3) And in the same lease time period, whether the conversion of the lease and the tax rate of different tax-containing types of the same time type is correct or not.

If the tax free lease is 10000 yuan and the tax rate is 6%, the tax containing lease should be 10600 yuan.

When auditing is carried out, a plurality of amount information in the same lease time period is firstly obtained from the key information, and each amount information comprises an original monetary value, a time type, an area type and a tax-containing type. For example: 1/2012-6/2013, the house rents 100 yuan, namely 3000 yuan/month. And (3) injection: the contract illustrates a tax rate of 6%. The area of the house is 50 square meters.

The extracted amount information is:

original monetary value	Rental period	Time type	Area type	Tax-containing type
					100	2012-7-1～2016-6-30	Daily rent of money	Rent of non square meter	Does not contain tax
3000	2012-7-1～2016-6-30	Moon rent	Rent of non square meter	Does not contain tax

As can be seen from the above table, the two pieces of amount information are different in time type, and in this case, the original coin value corresponding to the daily rent can be normalized to the original coin value of the monthly rent, taking 30 days as an example for one month: the normalization formula is as follows: daily rent amount 30 = monthly rent amount; thus, the daily rent is 100 yuan, and the monthly rent should be 3000 yuan. It can be appreciated that the normalized formula between monthly and yearly rentals is: monthly rent amount 12 = annual rent amount.

It can be understood that the above embodiment only provides normalization methods with different time types, and for the raw currency values with different area types, the normalization formula is as follows: non-square meter lease amount = square meter lease amount. For the original monetary values with different tax types, the normalization formula is as follows: tax-containing rent = tax-free rent (1 + tax rate of rent).

After normalization is completed, a comparison of the raw monetary value is made, for example: and comparing the original currency value obtained after the daily rent is normalized with the original currency value which is the monthly rent, if the original currency value is consistent with the original currency value, determining the contract information specification, otherwise, determining that the contract information is not specification.

On the basis of the embodiment, the key information further comprises amount change information, wherein the amount information comprises a basic amount and a changed amount; the step of auditing the key information by using the corresponding auditing model to obtain auditing results comprises the following steps:

calculating according to the basic amount and the amount change information to obtain an estimated changed amount;

and comparing the predicted changed amount with the changed amount, and if the predicted changed amount is inconsistent with the changed amount, determining that the contract information is not standard.

In a specific implementation, the amount change information may be understood as a status of floating or falling of the rent, for example: the first annual lease is two-ten thousand-two-thousand-eight-minute (932867.28-yuan) by the method of dewing, which comprises the steps of reading, loading, and the like, from the second lease year, the annual lease is increased by 5% year by year on the basis of the lease standard of the last lease year, namely, the second lease annual lease is a four-point Qiyan of ten-up Moqian Wu, the third lease annual lease is a four-point Qiyan of one hundred thousand, the fourth lease annual lease is a four-point Qiyan of one hundred thousand, the third lease is a four-point Qiyan of one hundred thousand, the fourth lease is a four-point Qiyan of one hundred thousand, the fifth lease is a four-point Qiyan of one hundred thousand, the four-point Qiyan of one 1134124.76. And (3) injection: the rental period is 30 days from 7.1 in 2017 to 6.30 in 2022. Among the contract information, "5% increments year by year" is the amount change information. And the first lease annual lease is: jiujia Sanwantwo Qian, liu She seven-element two-angle baqi (932867.28 yuan) is the basic amount.

From analysis of lease changes, several results are known:

results 1: (the second year)

Varying time: 8.1.2017 to 31.7.2018; the mode of variation is as follows: 1y, i.e. 1y; fluctuation width: 5%; the current month rent (without tax) value of the original coin: 81625.89.

results 2: (third year)

Varying time: 8.1.2018-7.31.2019; the mode of variation is as follows: 1y, i.e. 1y; fluctuation width: 5%; the current month rent (without tax) value of the original coin: 85707.18; other results were omitted.

Taking result 1 as an example, the starting time is 2017, 8, 1 and the ending time is 2018, 7, 31, the original monetary value of the corresponding time is respectively compared, and if the original monetary value is consistent (two digits after rounding to reserve decimal places), the lease change situation is consistent with lease description. Otherwise, the description is inconsistent, and the report check point is inconsistent with the corresponding lease description.

It should be noted that the time information and the amount information need to be normalized before the comparison is consistent, and may be normalized according to the rule expression in the following table:

wherein s refers to the date of the start of the rental period; e refers to the date of the end of the rental period; the method comprises the steps of (1) extracting contents regularly matched in a first bracket and carrying out numerical normalization; and $2 refers to taking the regularly matched content in the second bracket and carrying out numerical normalization. The variation pattern includes two dimensional attributes, one is a variation trend and one is a variation frequency. The trend dimension includes: an increment, a de-increment, a fixed three attributes; the frequency of variation includes: 1 year (1 y in the example), 2 years, etc. For example, "increment, interval 1y" is changed in an increasing manner year by year; the mode of fluctuation of "increment", once "or" increment, once "is one-time fluctuation; the mode of variation of "fixed" is unchanged; "amount" means to vary by number; "percentage" means varying in percentage.

For example: the rents are increased by 8% year by year on the basis of last year rents from the second year to the fourth year. And (3) injection: rental period from 20 days 6 in 2010 to 19 days 6 in 2015.

The start time of the change time is the start time of the rental period [2 (second year) -1], i.e., 20 days of 2011, 6 months. The end time of the change time is the start time +4 of the rental period (fourth year), i.e., 6 months and 20 days in 2014.

It should be noted that, the normalization manner of the amount information is identical to that of the above embodiment, and will not be described herein.

Fig. 2 is a schematic structural diagram of an apparatus provided in an embodiment of the present application, where the apparatus may be a module, a program segment, or a code on an electronic device. It should be understood that the apparatus corresponds to the embodiment of the method of fig. 1 described above, and is capable of performing the steps involved in the embodiment of the method of fig. 1, and specific functions of the apparatus may be referred to in the foregoing description, and detailed descriptions thereof are omitted herein as appropriate to avoid redundancy. The device comprises: an information extraction module 201 and an information auditing module 202, wherein:

the information extraction module 201 is configured to obtain contract information, and extract information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information; the information auditing module 202 is configured to audit each piece of key information by using a corresponding auditing model, so as to obtain an auditing result.

Based on the above embodiment, the information auditing module 202 is specifically configured to:

performing numerical conversion on the suspected capitalized amount;

On the basis of the above embodiment, the time information includes a contract period start time, a contract period end time, a contract period start time, and a contract period end time; the information auditing module 202 is specifically configured to:

On the basis of the embodiment, the key information further comprises amount change information, wherein the amount information comprises a basic amount and a changed amount; the information auditing module 202 is specifically configured to:

On the basis of the above embodiment, the information extraction module 201 is specifically configured to:

In summary, according to the embodiment of the application, the contract information is automatically extracted, and each piece of extracted key information is automatically audited, so that manual participation is not needed, human resources are saved, and auditing efficiency and accuracy are improved.

Fig. 3 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present application, as shown in fig. 3, where the electronic device includes: a processor (processor) 301, a memory (memory) 302, and a bus 303; wherein, the liquid crystal display device comprises a liquid crystal display device,

the processor 301 and the memory 302 perform communication with each other through the bus 303;

the processor 301 is configured to invoke the program instructions in the memory 302 to perform the methods provided in the above method embodiments, for example, including: acquiring contract information, and extracting information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information; and for each piece of key information, auditing the key information by using a corresponding auditing model to obtain an auditing result.

The processor 301 may be an integrated circuit chip with signal processing capabilities. The processor 301 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. Which may implement or perform the various methods, steps, and logical blocks disclosed in embodiments of the present application. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Memory 302 may include, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), and the like.

The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of performing the methods provided by the above-described method embodiments, for example comprising: acquiring contract information, and extracting information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information; and for each piece of key information, auditing the key information by using a corresponding auditing model to obtain an auditing result.

The present embodiment provides a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: acquiring contract information, and extracting information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information; and for each piece of key information, auditing the key information by using a corresponding auditing model to obtain an auditing result.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.

Further, the units described as separate units may or may not be physically separate, and units displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Furthermore, functional modules in various embodiments of the present application may be integrated together to form a single portion, or each module may exist alone, or two or more modules may be integrated to form a single portion.

In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A contract information auditing method, characterized by comprising:

acquiring contract information, and extracting information from the contract information to obtain at least one key information in the contract information; wherein the key information comprises amount information and time information;

aiming at each piece of key information, auditing the key information by using a corresponding auditing model to obtain an auditing result;

the extracting the information of the contract information to obtain at least one key information in the contract information includes:

extracting information from each row in the contract information by using a fifth regular expression, and taking the first character string as the key information if the fifth regular expression is matched with the first character string and the second character string and if the starting position of the first character string is smaller than or equal to the starting position of the second character string and the ending position of the first character string is larger than or equal to the ending position of the second character string;

the step of auditing the key information by using the corresponding auditing model to obtain auditing results comprises the following steps:

Performing numerical conversion on the suspected capitalized amount;

if the suspected capitalization amount is successfully matched with any one of the sub-expressions, determining that the suspected capitalization amount is not standard;

2. The method of claim 1, wherein the time information comprises a contract period start time, a contract period end time, a contract period start time, and a contract period end time; the step of auditing the key information by using the corresponding auditing model to obtain auditing results comprises the following steps:

3. The method of claim 1, wherein auditing the key information with the corresponding auditing model obtains auditing results, comprising:

4. The method of claim 1, wherein the key information further comprises amount change information, the amount information comprising a base amount and a changed amount; the step of auditing the key information by using the corresponding auditing model to obtain auditing results comprises the following steps:

5. A contract information auditing apparatus, characterized by comprising:

the information extraction module is used for acquiring contract information, extracting information from the contract information and acquiring at least one key information in the contract information; wherein the key information comprises amount information and time information;

the information auditing module is used for auditing the key information by utilizing a corresponding auditing model aiming at each key information to obtain an auditing result;

the information auditing module is specifically used for:

Performing numerical conversion on the suspected capitalized amount;

6. An electronic device, comprising: a processor, a memory, and a bus, wherein,

the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1-4.

7. A non-transitory computer readable storage medium storing computer instructions which, when executed by a computer, cause the computer to perform the method of any of claims 1-4.