Triggering information-based amount extraction method, equipment and medium

Abstract

The invention discloses an amount extraction method and device based on beacon information and a medium, and relates to the technical field of data processing. The method comprises the following steps: preprocessing a beacon text to obtain a beacon text in a target format, and performing keyword recognition in the beacon text in the target format to determine position information corresponding to keywords; searching in a preset range corresponding to the keyword according to the position information, and obtaining a corresponding amount expression in the beacon text; and identifying the amount expression, determining a corresponding amount type, and converting the amount expression according to the amount type to obtain an amount result in a specified format. According to the method, the efficiency and accuracy of information processing can be improved, the key amount information in the standard message text is effectively extracted, omission and misjudgment of the information are avoided, and the pertinence and practicability of data extraction are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and medium for extracting an amount based on bid information. Background Art

[0002] In today's rapidly changing business environment, bidding information, as a bridge connecting suppliers, buyers and various market participants, carries a large amount of key data on project bidding, commodity quotations, contract amounts, etc. The timely acquisition and accurate processing of this information plays an irreplaceable role in helping companies grasp market trends, optimize resource allocation, and formulate competitive strategies. However, with the increasing complexity and informatization of business activities, the release form of bidding information has also tended to be diversified and complex, including not only structured data tables, but also unstructured text descriptions, such as project overviews, quotation details, payment terms, etc.

[0003] In this context, the accurate extraction of the amount data in the bid information, as one of the core elements, has become a technical challenge. The amount information may not only be scattered in different locations in the text, but also use different currency units, number formats (such as the mixed use of Arabic numerals and Chinese characters), or even be embedded in complex sentence structures, which further increases the difficulty of extraction. Traditional information extraction techniques, such as rule-based methods or simple string matching, often have difficulty adapting to this highly variable and complex text environment, resulting in low extraction efficiency and high error rate.

[0004] In addition, with the rise of big data and artificial intelligence technology, enterprises' demand for information processing has expanded from single data extraction to deeper data mining and analysis. This requires that the amount extraction method should not only be able to accurately identify the amount value in the text, but also have a certain intelligent understanding ability to distinguish the meaning of the amount in different contexts (such as total price, unit price, prepayment, etc.), so as to provide more accurate data support for the decision-making of enterprises. Summary of the invention

[0005] The embodiments of the present application provide a method, device and medium for extracting an amount based on bid information, so as to solve the existing technical problems.

[0006] On the one hand, the embodiment of the present application provides a method for extracting an amount based on bid information, including:

[0007] Preprocessing the message text to obtain a message text in a target format, and performing keyword recognition in the message text in the target format to determine position information corresponding to the keyword;

[0008] According to the location information, searching is performed within a preset range corresponding to the keyword, and the corresponding amount expression in the bidding information text is obtained;

[0009] The amount expression is identified, a corresponding amount type is determined, and the amount expression is converted according to the amount type to obtain an amount result in a specified format.

[0010] In one implementation of the present application, the bid information text is preprocessed to obtain the bid information text in a target format, specifically including:

[0011] Receive a message text, and identify the message text to determine the non-text in the message file; wherein the non-text includes: spaces, line breaks and punctuation marks;

[0012] The spaces and line breaks in the message text are deleted, and the usage rules of punctuation marks in the message text after the deletion are unified to obtain the message text in the target format.

[0013] In one implementation of the present application, keyword recognition is performed in the target format of the target message text to determine the position information corresponding to the keyword, specifically including:

[0014] Obtaining historical bidding information texts within a preset time period, and determining keywords related to the amount in the historical bidding information texts; wherein the keywords at least include: total price, budget, successful bid, quotation and amount;

[0015] According to the keywords in the historical bidding information text, a corresponding keyword library is constructed, and based on the keyword library, the bidding information text in the target format is identified;

[0016] Determine the keywords in the message text, and determine the position information corresponding to the keywords in the message text.

[0017] In one implementation of the present application, based on the location information, searching within a preset range corresponding to the keyword and obtaining the corresponding amount expression in the bidding information text specifically includes:

[0018] According to the position information, locate the specific position of the keyword in the message text;

[0019] Based on the specific position of the keyword, a preset number of characters are respectively extended before and after the keyword to form a corresponding search range;

[0020] Within the search range, character strings related to the amount are identified and verified, so as to obtain the corresponding amount expression in the bid information text after the character string verification passes.

[0021] In one implementation of the present application, the amount expression is identified and the corresponding amount type is determined, specifically including:

[0022] Identify the character string corresponding to the amount expression to determine the components of the amount expression;

[0023] According to the components, the amount type corresponding to the amount expression is determined; wherein the amount type includes a combination of a number and a currency symbol, a combination of a number and a measurement unit, and a pure number.

[0024] In one implementation of the present application, before converting the amount representation according to the amount type to obtain an amount result in a specified format, the method further includes:

[0025] For an amount expression whose amount type is a combination of a number and a currency symbol, the default unit corresponding to the amount expression is yuan;

[0026] For an amount expression whose amount type is a combination of a number and a measurement unit, determining a unit corresponding to the amount expression; wherein the unit includes yuan and ten thousand yuan;

[0027] For an amount expression whose amount type is pure numbers, the default unit corresponding to the amount expression is yuan.

[0028] In one implementation of the present application, the amount expression is converted according to the amount type to obtain an amount result in a specified format, specifically including:

[0029] When the amount is expressed in yuan, the position of the first digit is determined by the LEAST and Locate functions, and the position of the last digit is determined by the GREATEST and CHAR_LENGTH functions.

[0030] According to the position of the first digit and the position of the last digit, the pure digits in the text are separated by using the SUBSTR function;

[0031] The ratio between the pure number and 10,000 is calculated to convert the unit of the amount into ten thousand yuan, and the amount result in the unit of ten thousand yuan is obtained.

[0032] In one implementation of the present application, after converting the amount representation according to the amount type to obtain an amount result in a specified format, the method further includes:

[0033] Compare the converted amount result with the preset amount format to determine whether two decimal places are retained in the amount result, whether the thousands separator of the amount result is used correctly, and whether the currency symbol of the amount result is placed correctly;

[0034] In the case where the comparison results are inconsistent, the format of the amount result is adjusted until the amount result matches the preset amount format, and the amount result after the format adjustment is stored in the database.

[0035] On the other hand, the embodiment of the present application further provides a device for extracting an amount based on bid information, the device comprising:

[0036] at least one processor;

[0037] and, a memory communicatively coupled to the at least one processor;

[0038] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method for extracting an amount based on bid information.

[0039] On the other hand, an embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, which, when executed, implements a method for extracting an amount based on bid information as described above.

[0040] The present application provides a method, device and medium for extracting an amount based on bid information, which at least have the following beneficial effects:

[0041] Through preprocessing and keyword recognition, the key information areas in the bidding text can be located quickly and accurately, laying a solid foundation for subsequent data extraction and processing, and improving the efficiency and accuracy of information processing; by accurately locating keywords and searching for amount expressions within their preset range, the key amount information in the bidding text can be effectively extracted, avoiding information omissions and misjudgments, and improving the pertinence and practicality of data extraction; through the identification and type determination of amount expressions, the specific meaning and purpose of the amount can be accurately understood, and then the format conversion can be performed, making the amount data more standardized and unified, facilitating subsequent data analysis and processing, and improving the efficiency and accuracy of data processing. At the same time, the amount results in the specified format are also more conducive to data storage, transmission and display, meeting the diverse needs in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 A flowchart of a method for extracting an amount based on bid information provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of the internal structure of an amount extraction device based on bid information provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0046] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0047] Figure 1 A flowchart of a method for extracting an amount based on bid information provided in an embodiment of the present application.

[0048] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.

[0049] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.

[0050] like Figure 1 As shown, an embodiment of the present application provides a method for extracting an amount based on bid information, including:

[0051] 101. Preprocess the message text to obtain a message text in a target format, and perform keyword recognition in the message text in the target format to determine position information corresponding to the keyword.

[0052] Specifically, in one embodiment of the present application, preprocessing the message text to obtain the message text in the target format specifically includes:

[0053] Receiving the bid information text and identifying the bid information text to determine the non-text text in the bid information file; wherein the non-text text includes: spaces, line breaks and punctuation marks;

[0054] The spaces and line breaks in the message text are deleted, and the usage rules of punctuation marks in the message text after deletion are unified to obtain the message text in the target format.

[0055] In one embodiment, assuming that a message text is received, first, according to the claim, the received message text is identified. By scanning the entire text, non-text text therein is determined, including: spaces (such as spaces between paragraphs), line breaks (such as the carriage return symbol at the end of each line), and punctuation marks (such as the semicolon and period in Chinese).

[0056] Next, delete the spaces and line breaks in the message text. After deletion, the text that was originally scattered across multiple lines is integrated into a continuous text, removing unnecessary spaces and carriage returns, making the text more compact and easier to read. Then, unify the rules for using punctuation marks in the message text after deletion. For example, replace the Chinese semicolon with the English comma, and replace the Chinese period with the English period to ensure the consistency and standardization of punctuation marks in the text.

[0057] After the above processing, the target format of the message text is obtained. At this time, the target format of the message text has removed spaces and line breaks, and the use of punctuation marks has also been unified, which provides convenience for subsequent text processing and analysis.

[0058] In one embodiment of the present application, keyword recognition is performed in the target format of the target message text to determine the position information corresponding to the keyword, specifically including:

[0059] Obtaining historical bidding information texts within a preset time period, and determining keywords related to the amount in the historical bidding information texts; wherein the keywords at least include: total price, budget, successful bid, quotation, and amount;

[0060] According to the keywords in the historical bidding information text, a corresponding keyword library is constructed, and based on the keyword library, the bidding information text in the target format is identified;

[0061] Determine the keywords in the bidding information text and determine the corresponding position information of the keywords in the bidding information text.

[0062] In one embodiment, suppose that a bidding information text analysis task about a construction project bidding is being processed, and the goal is to obtain historical bidding information texts within the past year (i.e., a preset time period) and extract keyword information related to the amount from them. First, according to the claims, historical bidding information texts within the preset time period (past year) are obtained. These texts may come from government announcements, bidding websites, or bidding records within an enterprise.

[0063] Next, we identified the keywords related to the amount in the historical bidding text. Through preliminary analysis of the text, we identified the following keywords: total price, budget, winning bid, quotation, and amount. These keywords are the ones that need to be focused on in subsequent analysis. Then, based on these keywords, we built a corresponding keyword library. This keyword library contains all the amount-related words of interest, as well as their possible variations and synonyms (for example, total price, budget, winning bid, etc.).

[0064] Next, based on the constructed keyword library, recognition is performed in the target format of the newsletter text. The target format here may be the newsletter text that has been preprocessed, non-text text removed and punctuation unified. Through keyword matching and text analysis technology, keywords and their positions can be accurately identified in the text.

[0065] Finally, the keywords in the bidding text were identified and their corresponding position information in the text was recorded. For example, it may be found that the word "total price" appears in the fifth line of the third paragraph of the text, and the word "budget" appears in the second line of the first paragraph, etc. This information is very important for subsequent data analysis and processing because it can quickly locate the key information area in the text.

[0066] 102. Based on the location information, search within the preset range corresponding to the keyword, and obtain the corresponding amount expression in the bidding information text.

[0067] Specifically, in one embodiment of the present application, based on the location information, searching is performed within a preset range corresponding to the keyword, and the corresponding amount expression in the bidding message text is obtained, specifically including:

[0068] According to the location information, locate the specific position of the keyword in the bidding text;

[0069] Based on the specific position of the keyword, the preset number of characters are respectively extended to the front and back of the keyword to form a corresponding search range;

[0070] Within the search scope, character strings related to the amount are identified and verified, so as to obtain the corresponding amount expression in the bid message text after the character string verification passes.

[0071] In one embodiment, it is assumed that the position information of the keyword "total price" in a certain bidding message text has been determined through the previous steps, specifically, the word appears in the seventh line of the third paragraph of the text. First, based on this position information, the specific position of the total price in the bidding message text is located. Through text parsing technology, the character position of the word "total price" in the text can be accurately found, for example, it may be the 100th to 102nd characters in the third paragraph.

[0072] Next, based on the specific position of the total price, the preset number of characters is extended forward and backward to form a corresponding search range. Assuming that the preset number of characters is 10, the search range starts from the 10th character before "total price" and ends at the 10th character after "total price", thus obtaining a search range that includes the total price and the 10 characters before and after it.

[0073] Then, in this search range, identify strings related to the amount. Since the amount is usually composed of numbers, currency symbols, and decimal points, these strings can be identified using techniques such as regular expressions. For example, strings such as "100,000 yuan" and "￥200,000.00" may be identified.

[0074] Finally, the recognized strings are verified to ensure that they are indeed valid expressions of amounts. Verification may include checking the format of the string, the validity of the numbers, and the correctness of the currency symbol. If the string verification passes, the corresponding amount expression in the bid message text is obtained. For example, within the above search range, "￥100,000.00" may be successfully identified and verified as the amount expression corresponding to the total price.

[0075] 103. Identify the amount expression, determine the corresponding amount type, and convert the amount expression according to the amount type to obtain the amount result in the specified format.

[0076] Specifically, in one embodiment of the present application, the amount expression is identified and the corresponding amount type is determined, which specifically includes:

[0077] Identify the character string corresponding to the amount expression to determine the components of the amount expression;

[0078] Determine the amount type corresponding to the amount expression based on the components; the amount types include a combination of numbers and currency symbols, a combination of numbers and measurement units, and pure numbers.

[0079] In one embodiment, suppose a character string corresponding to an amount expression is extracted from the bidding message text: "￥150,000.00 yuan". First, the character string corresponding to the amount expression is identified to determine its components. Through character string parsing, it can be identified that the character string contains the following parts: the currency symbol "￥", the number "150,000.00" and the unit of measurement "yuan".

[0080] Next, based on these components, determine the amount type corresponding to the amount expression. In this example, since the string contains numbers, currency symbols, and units of measurement at the same time, it can be determined that the amount type corresponding to this amount expression is a combination of numbers, currency symbols, and units of measurement.

[0081] If the string corresponding to the amount expression extracted from the bidding information text is "100 tons", then through recognition, it can be determined that its components are the number "100" and the unit of measurement "ton". Based on these components, it can be determined that the amount type corresponding to this amount expression is a combination of numbers and units of measurement.

[0082] If the string corresponding to the amount expression extracted from the bid information text is "50000", then through recognition, it can be determined that this string only contains pure numbers "50000". Therefore, it can be determined that the amount type corresponding to this amount expression is pure numbers.

[0083] In one embodiment of the present application, before converting the amount expression according to the amount type to obtain the amount result in a specified format, the following steps are included:

[0084] For the amount expression whose amount type is a combination of numbers and currency symbols, the default unit of the amount expression is yuan;

[0085] For the amount expression whose amount type is a combination of a number and a unit of measurement, determine the unit corresponding to the amount expression; the unit includes yuan and ten thousand yuan;

[0086] For the amount expression with pure number as the amount type, the default unit of the amount expression is yuan.

[0087] In one embodiment, it is assumed that multiple amount expressions have been extracted and identified from the bidding message text, and their corresponding amount types have been determined. Now, it is necessary to set a default or specific amount unit according to the amount type.

[0088] For the amount expression whose amount type is a combination of numbers and currency symbols:

[0089] If the amount extracted is expressed as "￥150,000.00", since it contains the currency symbol "￥" and the number "150,000.00", it can be determined that its amount type is a combination of a number and a currency symbol. According to the claims, the unit corresponding to this amount expression is RMB by default. Therefore, in this example, there is no need to determine the unit additionally, and the amount is directly considered to be RMB 150,000.00.

[0090] For the amount expression whose amount type is a combination of a number and a unit of measurement:

[0091] If the amount statement extracted is "1 million yuan" or "200 yuan", since they contain numbers and measurement units (ten thousand yuan or yuan), it can be judged that their amount types are a combination of numbers and measurement units. According to the claims, it is necessary to determine the unit corresponding to this amount statement. In this example, the unit of the first amount statement is ten thousand yuan, and the unit of the second amount statement is yuan. Therefore, it is necessary to record these two amount statements and their corresponding units separately.

[0092] For the amount type which is pure number, the following is the amount statement:

[0093] If the amount is expressed as "50000", since it only contains pure numbers, it can be determined that its amount type is pure numbers. According to the claims, the default unit corresponding to this amount expression is yuan. Therefore, in this example, there is no need to determine the unit additionally, and the amount is directly considered to be 50000 yuan.

[0094] In one embodiment of the present application, the amount expression is converted according to the amount type to obtain an amount result in a specified format, specifically including:

[0095] When the amount is expressed in yuan, the position of the first digit is determined by the LEAST and Locate functions, and the position of the last digit is determined by the GREATEST and CHAR_LENGTH functions.

[0096] According to the position of the first digit and the last digit, and using the SUBSTR function, separate the pure numbers in the text;

[0097] Calculate the ratio between the pure number and 10,000 to convert the unit of the amount into ten thousand yuan, and obtain the amount result in ten thousand yuan.

[0098] In one embodiment, it is assumed that a monetary amount expression "total amount: 123,456.78 yuan" is extracted from the bidding information text, and its corresponding unit has been determined to be yuan. Now, it is necessary to convert this monetary amount expression into ten thousand yuan.

[0099] First, determine the position of the first digit in the amount statement by using the LEAST and Locate functions (in actual applications, these functions may correspond to functions in a specific programming language or database query language, such as LEAST, LOCATE in MySQL or string processing functions in Python; the hypothetical function names are used as examples for illustration, and they need to be replaced with actual available functions during implementation). In this example, the position of the first digit "1" in "123,456.78" needs to be found. By scanning the string, it can be determined that the position of the first digit is the 9th character (assuming that the 6 characters "Total amount:" plus a space occupy the first 8 characters in total).

[0100] Next, the position of the last digit is determined by the GREATEST and CHAR_LENGTH functions. Again, these functions need to be replaced with specific string processing functions in actual applications. In this example, the position of the last digit "8" in "123,456.78" needs to be found. By scanning the string and considering its length, the position of the last digit can be determined to be the 16th character (the total length from "Total Amount:" minus 1, because string indexes usually start at 0).

[0101] Now that we know the position of the first and last digits, we can use the SUBSTR function (or equivalent function in the actual programming language) to extract the pure numbers in the text. In this example, we will extract the substring starting from the 9th character and ending at the 16th character, that is, "123,456.78". It should be noted that in actual applications, you may need to process characters such as commas and decimal points to ensure that pure numbers are extracted. This can be achieved by replacing or deleting these characters.

[0102] Finally, the extracted pure number "123456.78" (note that in actual operation, commas and invalid zeros after the decimal point need to be removed or rounded off) is compared with 10,000 to convert the amount into 10,000 yuan. In this example, 123456.78 divided by 10,000 equals 123,456,780 yuan. Therefore, the amount in 10,000 yuan is obtained.

[0103] In one embodiment of the present application, after converting the amount expression according to the amount type to obtain an amount result in a specified format, the following steps are included:

[0104] Compare the converted amount result with the preset amount format to determine whether two decimal places are retained in the amount result, whether the thousands separator of the amount result is used correctly, and whether the currency symbol of the amount result is placed correctly;

[0105] In the case of inconsistent comparison results, the format of the amount result is adjusted until the amount result matches the preset amount format, and the amount result after the format adjustment is stored in the database.

[0106] In one embodiment, it is assumed that a certain amount expression has been converted from RMB to 10,000 yuan, and a preliminary amount result, such as "123,456,780 yuan", has been obtained. Now, this amount result needs to be compared with the preset amount format, and necessary format adjustments need to be made.

[0107] First, the preset amount format is "XX.XX Ten Thousand Yuan", where "XX.XX" means that the amount is rounded to two decimal places and a thousand separator is used (in this example, the thousand separator does not actually appear because the amount is small, but it is necessary to check whether the format supports the correct use of the thousand separator). At the same time, it is stipulated that the currency symbol "Ten Thousand Yuan" should be placed after the amount digits, with a space between it and the digits.

[0108] Next, compare the converted amount "123,456,780 Yuan" with the preset amount format. The following problems were found: Extra digits were retained after the decimal point (6 instead of 2). Although there was no incorrect use of the thousands separator (because the amount was small), it was necessary to ensure that the format supported the correct placement of the thousands separator. There was no space between the currency symbol "10,000 Yuan" and the number.

[0109] To address these issues, the format of the amount results is adjusted:

[0110] Use rounding or truncation to adjust the number of decimal places to 2, resulting in "123,500 yuan". Confirm that the format supports the correct use of the thousands separator (in this example, due to the small amount, this step is actually not necessary, but for larger amounts, such as "12,345,600 yuan", you need to ensure the correct placement of the thousands separator ","). Add a space between the currency symbol "10,000 yuan" and the number to get "123,500 yuan".

[0111] After the format is adjusted, the amount result "123,500 yuan" that matches the preset amount format is obtained. Finally, the amount result after the format adjustment is stored in the database for subsequent data processing and analysis.

[0112] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, this application embodiment also provides a device for extracting the amount based on the bid information, and its structure is as follows: Figure 2 shown.

[0113] Figure 2This is a schematic diagram of the internal structure of a device for extracting money based on bid information provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0114] at least one processor;

[0115] and, a memory communicatively coupled to the at least one processor;

[0116] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the at least one processor to:

[0117] Preprocessing the message text to obtain the message text in the target format, and performing keyword recognition in the message text in the target format to determine the position information corresponding to the keyword;

[0118] According to the location information, search within the preset range corresponding to the keyword and obtain the corresponding amount expression in the bidding information text;

[0119] Identify the amount expression, determine the corresponding amount type, and convert the amount expression according to the amount type to obtain the amount result in the specified format.

[0120] The present application also provides a non-volatile computer storage medium storing computer executable instructions. When the computer executable instructions are executed, they can:

[0121] Preprocessing the message text to obtain the message text in the target format, and performing keyword recognition in the message text in the target format to determine the position information corresponding to the keyword;

[0122] According to the location information, search within the preset range corresponding to the keyword and obtain the corresponding amount expression in the bidding information text;

[0123] Identify the amount expression, determine the corresponding amount type, and convert the amount expression according to the amount type to obtain the amount result in the specified format.

[0124] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0125] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0126] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0127] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0128] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0131] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0132] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0133] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0134] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0135] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for extracting amount based on bidding information, characterized in that: The method comprises: Preprocessing the signal text to obtain the signal text in the target format, and performing keyword recognition in the signal text in the target format to determine the position information corresponding to the keyword; According to the location information, searching is performed within a preset range corresponding to the keyword, and the corresponding amount expression in the bidding information text is obtained; The amount expression is identified, a corresponding amount type is determined, and the amount expression is converted according to the amount type to obtain an amount result in a specified format.

2. The method for extracting the amount based on bid information according to claim 1, characterized in that: Preprocess the bid information text to obtain the bid information text in the target format, including: Receive a message text, and identify the message text to determine the non-text in the message file; wherein the non-text includes: spaces, line breaks and punctuation marks; The spaces and line breaks in the message text are deleted, and the usage rules of punctuation marks in the message text after the deletion are unified to obtain the message text in the target format.

3. The method for extracting the amount based on bid information according to claim 1, characterized in that: Keyword recognition is performed in the target format of the target message text to determine the position information corresponding to the keyword, specifically including: Obtaining historical bidding information texts within a preset time period, and determining keywords related to the amount in the historical bidding information texts; wherein the keywords at least include: total price, budget, successful bid, quotation and amount; According to the keywords in the historical bidding information text, a corresponding keyword library is constructed, and based on the keyword library, the bidding information text in the target format is identified; Determine the keywords in the message text, and determine the position information corresponding to the keywords in the message text.

4. The method for extracting the amount based on bid information according to claim 1, characterized in that: According to the location information, a search is performed within a preset range corresponding to the keyword, and the corresponding amount expression in the bidding information text is obtained, specifically including: According to the position information, locate the specific position of the keyword in the message text; Based on the specific position of the keyword, a preset number of characters are respectively extended before and after the keyword to form a corresponding search range; Within the search range, character strings related to the amount are identified and verified, so as to obtain the corresponding amount expression in the bid information text after the character string verification passes.

5. The method for extracting the amount based on bid information according to claim 1, characterized in that: Identify the amount statement and determine the corresponding amount type, including: Identify the character string corresponding to the amount expression to determine the components of the amount expression; According to the components, the amount type corresponding to the amount expression is determined; wherein the amount type includes a combination of a number and a currency symbol, a combination of a number and a measurement unit, and a pure number.

6. The method for extracting the amount based on bid information according to claim 1, characterized in that: Before converting the amount representation according to the amount type to obtain an amount result in a specified format, the method further includes: For an amount expression whose amount type is a combination of a number and a currency symbol, the default unit corresponding to the amount expression is yuan; For an amount expression whose amount type is a combination of a number and a measurement unit, determining a unit corresponding to the amount expression; wherein the unit includes yuan and ten thousand yuan; For an amount expression whose amount type is pure numbers, the default unit corresponding to the amount expression is yuan.

7. The method for extracting the amount based on bid information according to claim 6, characterized in that: According to the amount type, the amount expression is converted to obtain an amount result in a specified format, specifically including: When the amount is expressed in yuan, the position of the first digit is determined by the LEAST and Locate functions, and the position of the last digit is determined by the GREATEST and CHAR_LENGTH functions. According to the position of the first digit and the position of the last digit, the pure digits in the text are separated by using the SUBSTR function; The ratio between the pure number and 10,000 is calculated to convert the unit of the amount into ten thousand yuan, and the amount result in the unit of ten thousand yuan is obtained.

8. The method for extracting the amount based on bid information according to claim 1, characterized in that: After converting the amount representation according to the amount type to obtain an amount result in a specified format, the method further includes: Compare the converted amount result with the preset amount format to determine whether two decimal places are retained in the amount result, whether the thousands separator of the amount result is used correctly, and whether the currency symbol of the amount result is placed correctly; In the case where the comparison results are inconsistent, the format of the amount result is adjusted until the amount result matches the preset amount format, and the amount result after the format adjustment is stored in the database.

9. A device for extracting money based on bid information, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for extracting an amount based on bid information as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed, a method for extracting an amount based on bid information as described in any one of claims 1 to 8 is implemented.

Images