CN112580299A - Intelligent bid evaluation method, bid evaluation device and computer storage medium - Google Patents
Intelligent bid evaluation method, bid evaluation device and computer storage medium Download PDFInfo
- Publication number
- CN112580299A CN112580299A CN202011615092.6A CN202011615092A CN112580299A CN 112580299 A CN112580299 A CN 112580299A CN 202011615092 A CN202011615092 A CN 202011615092A CN 112580299 A CN112580299 A CN 112580299A
- Authority
- CN
- China
- Prior art keywords
- text
- sentence
- information
- bid
- sentences
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 53
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims description 35
- 238000001514 detection method Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 210000001072 colon Anatomy 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 239000007787 solid Substances 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 239000013074 reference sample Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000013590 bulk material Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/117—Tagging; Marking up; Designating a block; Setting of attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/109—Font handling; Temporal or kinetic typography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an intelligent bid evaluation method, a bid evaluation device and a computer storage medium, wherein the intelligent bid evaluation method comprises the following steps: acquiring a first element in a first text; searching first element information of the first element in the first text, and searching second element information of the first element in the second text; performing the same processing on the first element information and the second element information at the same time; wherein the first text is one of the bid-on text and the bid-on text, and the second text is the other of the bid-on text and the bid-on text. The intelligent bid evaluation method can simplify bid evaluation work and improve bid evaluation efficiency and accuracy.
Description
Technical Field
The application relates to the technical field of text processing, in particular to an intelligent bid evaluation method, bid evaluation equipment and a computer storage medium.
Background
Tender bidding is a common transaction mode in domestic and foreign trade, and is widely applied to businesses such as bulk material purchasing and the like. In this transaction mode, a buyer generally issues a bidding document as a tenderer, the bidding document generally includes information such as technical parameter requirements, quality requirements, after-sale service requirements, completion date requirements and the like of a purchased item, then the tenderer participates in bidding competition by providing the bidding document, finally the tenderer creates an evaluation committee consisting of industry experts to examine the qualification document of the tenderer to determine whether the tenderer has bidding qualification and to examine the conformity between the bidding document of the tenderer and the bidding document, so as to select the eligible tenderer as a candidate unit, and finally the evaluation committee scores according to the evaluation rules to select a winning unit from the candidate units.
At present, in the process of checking the compliance between the bidding documents and the bidding documents, only manual work is involved in the whole process, which not only costs a great amount of manpower, but also has low efficiency and is easy to cause the conditions of missed evaluation, wrong evaluation and the like.
Disclosure of Invention
The technical problem mainly solved by the application is to provide an intelligent bid evaluation method, bid evaluation equipment and a computer storage medium, which can simplify bid evaluation work and improve bid evaluation efficiency and accuracy.
In order to solve the technical problem, the application adopts a technical scheme that: an intelligent bid evaluation method is provided, and the method comprises the following steps: acquiring a first element in a first text; searching the first text for first element information of the first element, and searching the second text for second element information of the first element; performing the same processing on the first element information and the second element information at the same time; wherein the first text is one of a bid-on text and a bid-on text, and the second text is the other of the bid-on text and the bid-on text.
In order to solve the above technical problem, another technical solution adopted by the present application is: the evaluation device comprises a processor, a memory and a communication circuit, wherein the processor is respectively coupled with the memory and the communication circuit, and the processor controls the processor, the memory and the communication circuit to realize the steps of the method when in work.
In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a computer storage medium having stored thereon a computer program executable by a processor to perform the steps of the above method.
The beneficial effect of this application is: the bidding document searching method and the bidding document searching system can automatically search the element information of the first element in the bidding document and the bidding document, and simultaneously carry out the same processing on the two element information, on one hand, a user can rapidly and accurately make judgment on the conformity between the bidding document and the bidding document, on the other hand, the phenomena of missed evaluation and wrong evaluation can be avoided being searched manually, so that the bidding evaluation work can be simplified, and the bidding evaluation efficiency and accuracy are improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
FIG. 1 is a schematic flow chart diagram of an embodiment of the intelligent bid evaluation method of the present application;
FIG. 2 is a schematic flow chart diagram of another embodiment of the intelligent bid evaluation method of the present application;
FIG. 3 is a schematic flow chart diagram illustrating another embodiment of the intelligent bid evaluation method of the present application;
FIG. 4 is a schematic flow chart diagram illustrating another embodiment of the intelligent bid evaluation method of the present application;
FIG. 5 is a schematic structural diagram of an embodiment of the bid evaluation device of the present application;
FIG. 6 is a schematic structural diagram of an embodiment of a computer storage medium according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
First, it should be noted that the intelligent bid evaluation method in the present application is executed by a bid evaluation device, and the bid evaluation device may be any device with information processing capability, such as a mobile phone, a desktop computer, and a notebook computer, which is not limited herein.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of an intelligent bid evaluation method according to the present application, where the intelligent bid evaluation method includes:
s110: a first element in a first text is obtained.
Specifically, after receiving the element input by the user, the same element may be searched for in the first text, so as to obtain the first element in the first text, or after detecting that the user inputs a selection instruction in the first text, the first element selected by the user in the first text may be obtained.
The first text is one of a tendering text and a bidding text, that is, the first text is the tendering text or the bidding text, wherein the tendering text refers to a text issued by the purchasing party as the tendering party and includes each product to be purchased and the model number, quantity and the like of each product, and the bidding text refers to a text made by the bidding party in response to the bidding text in order to participate in bidding competition and includes each product that the bidding party can provide and the model number, quantity and the like of each product. In general, the bid text is modified based on the bid text.
Wherein the first element refers to a product in the first text, for example, for "processor configuration Intel Core I7 eight generation processor; memory: 8G and hard disk: 256G-SSD solid state disk. The number of the USB ports is 6, wherein the USB 3.0 has 4, and for the text, the first elements included in the text are "processor", "memory", "hard disk", "USB port", and "USB 3.0". The first element may be not only a physical product but also a service, a technology, or the like.
S120: first element information of the first element is searched in the first text, and second element information of the first element is searched in the second text.
Specifically, the second text is the other of the bid-on text and the bid-on text, that is, when the first text is the bid-on text, the second text is the bid-on text, and when the first text is the bid-on text, the second text is the bid-on text.
The first element information refers to description information related to the first element, such as quantity, specification, performance, and the like.
The second element information refers to description information on the same element as the first element in the second text. Specifically, since the bid document is generally modified on the basis of the bid document, both generally include the same elements.
S130: the first element information and the second element information are simultaneously subjected to the same process.
Specifically, the first element information and the second element information are subjected to the same processing operation at the same time, wherein the same processing operation includes, but is not limited to, highlighting, processing according to an operation instruction input by a user, and the like.
And carrying out the same processing on the first element information and the second element information at a moment, so that the first element information and the second element information in the first text present the same effect to a user.
In an application scenario, step S110 specifically includes: the first element information and the second element information are simultaneously highlighted. The first element information and the second element information are highlighted, so that the first element information and the second element information are more striking, and a user can quickly and accurately judge the conformity between the bidding text and the bidding text. Among them, the first element information and the second element information are highlighted in the following ways: the first element information and the second element information are respectively displayed in the first text and the second text in a manner of highlighting, underlining, or bolding, or a popup window including the first element information and the second element information is popped up, or the first element information and the second element information are displayed in a single paragraph, in short, as long as the first element information and the second element information are more noticeable, and the specific manner is not limited.
In other application scenarios, step S110 may also be: and according to an operation instruction input by a user, simultaneously performing operation processing corresponding to the operation instruction on the first element information and the second element information. Specifically, at this time, the user also inputs an operation command, for example, underlines a certain element, and when the operation command input by the user is received, the operation processing corresponding to the operation command is performed on the first element information, and the operation processing corresponding to the operation command is performed on the second element information, and both the operation processing and the operation processing are performed simultaneously.
It can be seen from the above contents that, in the embodiment, the element information of the first element in the bid text and the bid text can be automatically found, and the two element information are processed in the same way, so that on one hand, a user can conveniently and accurately judge the conformity between the bid text and the bid text, and on the other hand, the phenomena of missed evaluation and wrong evaluation caused by manual searching can be avoided, thereby simplifying the bid evaluation work and improving the bid evaluation efficiency and accuracy.
Referring to fig. 2, fig. 2 is a schematic flow chart of another embodiment of the intelligent bid evaluation method of the present application, including:
s210: a first sentence currently located in the first text by the user is determined.
Specifically, when a user locates a sentence in the first text, it indicates that the user wants to view related elements in the located sentence.
The first sentence currently located in the first text by the user may be a sentence where the character currently selected by the user is located, or may also be a sentence where a cursor of the remarking device is located, that is, at this time, the character selected by the user may be obtained, and then the sentence where the selected character is located is determined as the first sentence currently located in the first text, or the sentence where the cursor of the remarking device is located is determined as the first sentence currently located in the first text. How to determine the sentence located by the user is not limited in the present application.
The first sentence in positioning may be a sentence ending in a period, a comma, a semicolon, or a pause, which is not limited herein.
S220: and performing element identification and entity information identification on the first sentence to obtain a first element and entity information of the first element in the first text.
Specifically, after element recognition is carried out on a first sentence, an element in the first sentence, namely a first element in a first text, is obtained; and after the entity information of the first sentence is identified, the entity information in the first sentence is obtained, namely the entity information of the first element.
The entity information includes at least one of a brand name, an item model number, and a quantitative index. The quantitative index refers to at least one of the number and the size of the articles.
The element recognition and the entity information recognition can be performed on the first sentence by using a pre-established database, or the element recognition and the entity information recognition can be performed on the first sentence by using a pre-trained recognition model.
In an application scenario, in order to improve the processing speed, a named recognition model is trained in advance, and element recognition and entity information recognition are carried out on a first sentence at the same time. Specifically, the first sentence is input into a pre-trained naming recognition model for recognition, and a first element and entity information of the first element in the first text are obtained. The named recognition model is pre-trained based on deep learning, and can recognize an element in the received sentence and entity information of the element. Specifically, after the first sentence is input into the named recognition model, the named recognition model correspondingly outputs the first element and the entity information of the first element, for example, after the sentence "processor configured Intel Core I7 eight generation processor" is input into the named recognition model trained in advance, the named recognition model outputs the following contents: the processor is named Intel, and the model of the processor is Core I7 eight generations.
It is understood that when there is no entity information in the input sentence, the named recognition model only outputs the elements in the sentence, for example, the sentence "memory: 8G and hard disk: after the 256G-SSD solid state disk' inputs a naming recognition model, the output content of the naming recognition model is as follows: memory, hard disk.
In other embodiments, the element and entity information in the first sentence may be identified by two different models.
S230: and identifying the element value of the first sentence according to the first element to obtain the element value of the first element in the first text.
Specifically, the element value of the first element refers to information directly describing the first element, that is, the element value recognition of the first sentence from the first element refers to finding information directly describing the first element in the first sentence. It is understood that the value of the element of the first element includes entity information of the first element.
In an application scenario, in order to improve the processing speed, a reading understanding model is trained in advance to identify the element value of a first sentence, specifically, the first sentence and a first element are input into the reading understanding model trained in advance to be identified, and the element value of the first element in a first text is obtained.
The reading understanding model is also trained in advance based on deep learning, wherein an element name and a related sentence are input, an element value corresponding to the element name is output, the output element value can be a single value or a combination of multiple values, that is, when multiple element values corresponding to the same element exist in the input sentence, the reading understanding model can output all the multiple element values.
Wherein a sentence and a plurality of elements in the sentence can be input into the reading understanding model, and the reading understanding model correspondingly outputs the element values of the plurality of elements, for example, for a processor configured with an Intel Core I7 eight generation processor; memory: 8G and hard disk: 256G-SSD solid state disk. For 6 USB ports, wherein USB 3.0 has 4 sentences, after identifying 5 elements including the processor, the memory, the hard disk, the USB port, and USB 3.0 in step S220, the sentences and the 5 elements are input into the reading comprehension model for identification, and the element value of the element of the processor is Intel Core I7 eighth-generation processor, the element value of the element of the memory is 8G, the element value of the element of the hard disk is 256G-SSD solid state disk, the element value of the element of the USB port is 6, and the element value of the element of the USB 3.0 is 4, and the specific correspondence relationship can be seen in one of the following tables:
table-element name and element value correspondence
During recognition, the first sentence and the first element may be input into the reading understanding model at a certain time interval, or the first sentence and the first element may be spliced according to a preset rule and then input into the reading understanding model.
S240: a second sentence is looked up in the second text that is aligned with the first sentence.
Specifically, the first sentence is aligned with the second sentence, which means that the position of the first sentence in the first text is the same as the position of the second sentence in the second text, and considering that the bid document is usually modified on the basis of the bid document, both have an obvious characteristic that the two texts keep consistent precedence order in terms of description of elements, so that the two sentences in the first text and the second text with the same position may describe the same elements.
The sentence number of the first sentence in the first text can be found, and then the second sentence aligned with the first sentence can be found in the second text according to the sentence number, wherein the sentence number indicates that the first sentence is the second sentence in the first text. For example, if the sentence number of the searched first sentence is 5 (i.e., the first sentence is the 5 th sentence in the first text), the 5 th sentence is searched in the second text, so that the searched sentence is the second sentence. When the sentence numbers in the first text and the second text are judged, the sentence ending with the preset punctuation mark is taken as a sentence, for example, the preset punctuation mark is taken as a sentence, and the sentence ending with the sentence is taken as a sentence in the first text and the second text.
S250: and performing element identification and entity information identification on the second sentence to obtain a second element corresponding to the first element and entity information of the second element in the second text.
Specifically, the process is similar to step S220, and specific contents can be referred to above, and are not described herein again.
S260: and identifying the element value of the second sentence according to the second element to obtain the element value of the second element in the second text.
Specifically, the process is similar to step S230, and specific contents can be referred to above, and are not described herein again.
S270: first element information including entity information and element values of a first element and second element information including entity information and element values of a second element are simultaneously subjected to the same process.
Specifically, since the element information in the present embodiment includes the element value and the entity information, the entity information and the element value of the first element and the entity information and the element value of the second element are simultaneously processed when the processing is performed.
When the process in step S270 indicates highlighting, the element value includes entity information, and the object of displaying both the entity information and the element value is to emphasize the entity information.
When the first element information and the second element information are highlighted, the first element and the second element may be simultaneously highlighted, for example, a pop-up window is popped up, the first element and the first element information and the second element information are displayed in the pop-up window, and when displayed, the first element and the first element information are displayed in association with each other, and the second element information are displayed in association with each other.
Although the above-mentioned descriptions have been provided for the scheme of the present application in steps S210 to S270, it does not mean that the scheme of the present application is necessarily performed in the order of steps S210 to S270, that is, the technical scheme of the present application may disturb the above-mentioned order, for example, step S230 may be performed after step S240 or step S250.
Meanwhile, when the first sentence and the second sentence are recognized, the pre-trained naming recognition model and the reading understanding model are adopted, so that the conditions of wrong evaluation and missed evaluation during manual evaluation can be avoided.
In other embodiments, step S260 may be replaced with: and identifying the element value of the second sentence according to the first element to obtain the element value of the first element in the second text. In this case, it is possible to avoid the situation in which, in some cases, the second sentence has no first element at all, but the value of the element is recognized.
Referring to fig. 3, fig. 3 is a schematic flow chart of another embodiment of the intelligent bid evaluation method of the present application, including:
s301: and respectively carrying out format check and correction on the first text and the second text.
Specifically, considering that the tenderer cannot strictly meet the specification requirements of bidders on writing formats, part of bidders have randomness on writing formats, and punctuation marks are mistakenly used or replaced by "spaces", "line feed characters" and "TAB keys", which may cause difficulty in increasing subsequent element distinguishing and reduce efficiency of the whole processing process. In other embodiments, if the formats of the first text and the second text can be strictly specified, step S301 may not be executed in this case.
When format checking and correcting are performed, correction may be performed according to a preset policy, where the preset policy indicates what kind of errors should be corrected, for example, the preset policy is: all spaces in the text are replaced with empty characters.
In an application scenario, in order to improve the processing speed and improve the accuracy of correction, a pre-trained punctuation error detection model is used for respectively carrying out format check and correction on a first text and a second text. Wherein, the punctuation error detection model is trained in advance. In an application scenario, in the process of training the model, in order to ensure the error detection effect of the final model, open source news data with a more standard format can be collected as training data of the model, and meanwhile, in order to ensure the accuracy of the training data so as to further improve the error detection effect of the final model, punctuations and punctuations in the training data can be manually corrected, and finally, training is performed based on the corrected data.
In an application scene, in order to reduce the identification difficulty of the punctuation error detection model and enable the final correction effect to be more accurate, the punctuation error detection model keeps punctuation marks in the original text and only predicts the positions without the punctuation marks when respectively carrying out format check and correction on the first text and the second text, so that the contextual punctuation information can be fully utilized in the identification process, and the final correction accuracy is improved. For example, for "space", "linefeed", "TAB key", etc. in the first text or the second text, the punctuation error detection model considers which cases are used instead of punctuation marks and which cases do not represent any meaning, and if used instead of punctuation marks, adds punctuation marks at corresponding positions, and if not, adds null characters at corresponding positions.
In an application scenario, the prediction tag of the punctuation error detection model includes at least one of a colon, a comma, a period, a line break, and a null character. The empty character means that no punctuation mark should be added at the current position, and the line feed character is used at the end position of each element to play another role of one line.
For example, when the prediction tag of the punctuation error detection model includes a colon, a comma, a period, a line break and a null character, when the punctuation error detection model predicts a position where the punctuation symbol is not located, it predicts whether the position should be a colon, a comma, a period, a line break or a null character, and if the position is not one of the colon, the comma, the period, the line break and the null character, it does not correct, and if the position is one of the colon, the comma, the period, the line break and the null character, it corresponds to a correction.
Referring to table two below, after the original text as follows is input into the punctuation error detection model, the punctuation error detection model outputs a check-corrected text.
Comparison of Table two original text with error-checked text
It is understood that after step S301, the first text and the second text are already files in a canonical format, and then the subsequent steps are performed based on the corrected first text and second text.
S302: and performing word segmentation processing on each sentence in the first text and each sentence in the second text respectively to obtain a first word sequence and a second word sequence.
Specifically, the process of performing word segmentation is to split a sentence into a plurality of words, where the sentence refers to a sentence ending with a period, a comma, a semicolon, or a pause sign.
When performing word segmentation processing, the word segmentation processing may be performed based on a dictionary word segmentation algorithm, or may be performed based on a statistical machine learning algorithm, which is not limited herein.
After word segmentation processing, a first word sequence corresponding to the first text and a second word sequence corresponding to the second text are obtained.
S303: and respectively recording mapping relations between each sentence in the first text and each sentence in the second text and each included word.
Specifically, for a sentence in the first text or the second text, which includes at least one word, there is a mapping relationship between the sentence and the at least one word, that is, the sentence corresponds to the at least one word.
In an application scenario, the correspondence between a sentence and included words is recorded by the starting position of the word corresponding to the sentence. Specifically, the words in the first word sequence and the second word sequence are respectively ordered according to the sequence in the first text and the second text, then the words in the first word sequence and the second word sequence are respectively numbered from 0, then the number of the first word and the number of the last word included in the words are recorded corresponding to each sentence in the first text and the second text, and then a plurality of words included in the words can be found in the corresponding sequence according to the recorded number of the first word and the recorded number of the last word corresponding to a sentence in the first text or the second text, thereby realizing the mapping relationship between the recorded sentences and the words.
S304: and aligning the words in the first word sequence with the words in the second word sequence.
Specifically, aligning the words in the first word sequence with the words in the second word sequence means matching the same or similar words in the first word sequence and the second word sequence, and establishing a corresponding matching relationship.
In an application scenario, considering that the bid text is usually modified on the basis of the bid text, and therefore has an obvious characteristic that the two are substantially consistent in terms of element description, based on this, the present embodiment uses a minimum edit distance algorithm to align the words in the first word sequence with the words in the second word sequence, and specifically, during the process, one of the first word sequence and the second word sequence is used as a reference sample, and the other is converted into a reference sample with a minimum number of add-delete operations. Wherein, when processing is performed by using the minimum edit distance algorithm, the operations involved include deleting a word, inserting a word, and replacing a word.
In the application scene, words in the first word sequence and words in the second word sequence are aligned by using a minimum edit distance algorithm, and even if a large number of similar words exist in the first word sequence and the second word sequence, the phenomenon of wrong alignment is not easy to occur.
In other application scenarios, words in the first word sequence and the second word sequence may also be aligned according to similarity between the words.
S305: according to the mapping relations among the sentences in the first text, the sentences in the second text and the words included in the first text and the second text, the alignment relation between the words in the first word sequence and the words in the second word sequence is converted into the alignment relation between the sentences in the first text and the sentences in the second text, and the sentences in the first text and the sentences in the second text are aligned.
Specifically, after aligning the words in the first word sequence and the words in the second word sequence, according to the mapping relationship recorded before, the alignment relationship between the words and the words can be converted into the alignment relationship between the sentences, so that the sentences in the first text and the sentences in the second text are aligned. After sentence alignment is achieved, a one-to-one situation may occur, or a one-to-many situation may occur, where a one-to-one situation refers to one sentence being aligned with one sentence, and a one-to-many situation refers to one sentence being aligned with two or more sentences (the two or more sentences describe the same element).
For example, as shown in table three below, after alignment, the sentences in the first text and the sentences in the second text establish a corresponding relationship.
Corresponding relation of aligned first text and second text of table III
In the third table, the "wired network card and wireless network card that need to be built in" in the first text does not have similar contents in the second text, so that no corresponding sentence is aligned with the second text.
S306: a first sentence currently located in the first text by the user is determined.
S307: and performing element identification and entity information identification on the first sentence to obtain a first element and entity information of the first element in the first text.
S308: and identifying the element value of the first sentence according to the first element to obtain the element value of the first element in the first text.
S309: a second sentence is looked up in the second text that is aligned with the first sentence.
S310: and performing element identification and entity information identification on the second sentence to obtain a second element corresponding to the first element and entity information of the second element in the second text.
S311: and identifying the element value of the second sentence according to the second element to obtain the element value of the second element in the second text.
S312: first element information including entity information and element values of a first element and second element information including entity information and element values of a second element are simultaneously subjected to the same process.
The contents of steps S306 to S312 are the same as the contents of steps S210 to S270 in the above embodiment, and reference may be made to the above embodiment specifically, and details are not repeated here.
In the embodiment, the first text and the second text are subjected to format check and correction in advance, and the sentences in the first text and the sentences in the second text are subjected to alignment processing, so that the first text and the second text are clearer in structure, favorable conditions are provided for subsequent processing, and the processing speed of the bid evaluation is improved.
Meanwhile, in the embodiment, after the first text and the second text are checked and corrected, the corrected first text and the corrected second text can be directly displayed to a user in the bid evaluation process, so that the user can read the corrected first text and the corrected second text conveniently.
Referring to fig. 4, fig. 4 is a schematic flow chart of another embodiment of the intelligent bid evaluation method of the present application, including:
s410: a first sentence currently located in the first text by the user is determined.
S420: and performing element recognition on the first sentence to obtain a first element in the first text.
S430: and identifying the element value of the first sentence according to the first element to obtain the element value of the first element in the first text.
S440: a second sentence is looked up in the second text that is aligned with the first sentence.
S450: and identifying the element value of the second sentence according to the first element to obtain the element value of the first element in the second text.
S460: and simultaneously carrying out the same processing on the element value in the first text and the element value in the second text.
Unlike the above-described embodiment, on the one hand, the first element information and the second element information each include only an element value, and on the other hand, when the element value of the first element in the second text is acquired, the second sentence is recognized from the first element without recognizing the second element in the second sentence, so that it is possible to avoid a situation where the element value is recognized even though the second sentence has no first element at all (the first sentence and the second sentence are aligned by making an error in alignment, but the first sentence and the second sentence are not described as the same element), and further, the processing speed can be increased in the present embodiment.
In other embodiments, step S440 and step S450 may also be replaced with: and identifying the second text according to the first element to obtain an element value of the first element in the second text. It should be noted that, although it is not necessary to search for the second sentence aligned with the first sentence to increase the processing speed, there is a drawback that the second sentence is not close to the user's intention, and the following description is made with reference to specific examples:
suppose a school needs to purchase two desktop computers, one for a teacher and the other for a student, which are configured differently, and there are two sentences in the first text and the second text, the first sentence describing a processor of the desktop computer for the student, and the second sentence describing a processor of the desktop computer for the teacher. In the bid evaluation process, if a user (a bid evaluator) wants to see the coincidence of two documents with respect to a desktop computer for a student, it is assumed that the user selects a plurality of characters in a first sentence in a first text, then the bid evaluation device identifies the first sentence to obtain the information of an element in the first sentence as a processor and corresponding element information, and then if a full text of a second text is identified according to the element of the processor, the obtained element information includes both description information of the desktop computer for the student and description information of a computer for a teacher, and obviously, the finally presented result is not the result that the user wants to obtain.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of the bid evaluation device of the present application. The bid evaluation device 200 includes a processor 210, a memory 220, and a communication circuit 230, wherein the processor 210 is coupled to the memory 220 and the communication circuit 230, respectively, the memory 220 stores program data, and the processor 210 implements the steps of the method according to any of the above embodiments by executing the program data in the memory 220, and the detailed steps can be referred to the above embodiments and are not described herein again.
The bid evaluation device 200 may be any device with information processing capability, such as a mobile phone, a desktop computer, and a notebook computer, without limitation.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of a computer storage medium according to the present application. The computer storage medium 300 stores a computer program 310, the computer program 310 being executable by a processor to implement the steps of any of the methods described above.
The computer storage medium 300 may be a device that can store the computer program 310, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, or may be a server that stores the computer program 310, and the server may send the stored computer program 310 to another device for operation, or may self-operate the stored computer program 310.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.
Claims (12)
1. An intelligent bid evaluation method, characterized in that the method comprises:
acquiring a first element in a first text;
searching the first text for first element information of the first element, and searching the second text for second element information of the first element;
performing the same processing on the first element information and the second element information at the same time;
wherein the first text is one of a bid-on text and a bid-on text, and the second text is the other of the bid-on text and the bid-on text.
2. The method of claim 1, wherein the step of obtaining the first element in the first text comprises:
determining a first sentence currently positioned in the first text by the user;
and performing element recognition on the first sentence to obtain the first element in the first text.
3. The method according to claim 2, wherein the first element information and the second element information each include an element value; the step of searching for the first element information of the first element in the first text includes:
and performing element value identification on the first sentence according to the first element to obtain an element value of the first element in the first text.
4. The method according to claim 3, wherein the step of searching the second text for the second element information of the first element comprises:
searching for a second sentence in the second text that is aligned with the first sentence;
element recognition is carried out on the second sentence, and a second element corresponding to the first element in the second text is obtained;
and identifying the element value of the second sentence according to the second element to obtain the element value of the second element in the second text.
5. The method according to claim 4, wherein each of the first factor information and the second factor information further includes entity information including at least one of a brand name, an item model number, and a quantitative index; the method further comprises the following steps:
carrying out entity information identification on the first sentence to obtain entity information of the first element in the first sentence;
and identifying entity information of the second sentence to obtain entity information of the second element in the second sentence.
6. The method according to claim 3, wherein the step of searching the second text for the second element information of the first element comprises:
searching for a second sentence in the second text that is aligned with the first sentence;
and performing element value identification on the second sentence according to the first element to obtain an element value of the first element in the second text.
7. The method according to claim 4 or 6, wherein before the step of obtaining the first element in the first text, the method further comprises:
performing word segmentation processing on each sentence in the first text and each sentence in the second text respectively to obtain a first word sequence and a second word sequence;
respectively recording mapping relations among all sentences in the first text, all sentences in the second text and words included in the sentences;
aligning words in the first word sequence with words in the second word sequence;
according to the mapping relations among the sentences in the first text, the sentences in the second text and the words included in the first text, the alignment relations among the words in the first word sequence and the words in the second word sequence are converted into the alignment relations among the sentences in the first text and the sentences in the second text, and the sentences in the first text and the sentences in the second text are aligned.
8. The method according to claim 7, wherein before the step of performing word segmentation processing on each sentence in the first text and each sentence in the second text, respectively, the method further comprises:
and respectively carrying out format check and correction on the first text and the second text.
9. The method of claim 8, wherein the step of format checking and correcting the first text and the second text, respectively, comprises:
and respectively carrying out format check and correction on the first text and the second text by using a pre-trained punctuation error detection model.
10. The method of claim 9, wherein the punctuation error detection model performs symbol prediction on positions where punctuation symbols are not located when the first text and the second text are checked and corrected for format, respectively, and wherein a prediction tag of the punctuation error detection model comprises at least one of a colon, a comma, a period, a line break, and a null character.
11. A bidding device, comprising a processor, a memory, and a communication circuit, wherein the processor is coupled to the memory and the communication circuit, respectively, and wherein the processor is operative to control itself and the memory and the communication circuit to implement the steps of the method according to any one of claims 1-10.
12. A computer storage medium, characterized in that the computer storage medium stores a computer program executable by a processor to implement the steps in the method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011615092.6A CN112580299A (en) | 2020-12-30 | 2020-12-30 | Intelligent bid evaluation method, bid evaluation device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011615092.6A CN112580299A (en) | 2020-12-30 | 2020-12-30 | Intelligent bid evaluation method, bid evaluation device and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112580299A true CN112580299A (en) | 2021-03-30 |
Family
ID=75144821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011615092.6A Pending CN112580299A (en) | 2020-12-30 | 2020-12-30 | Intelligent bid evaluation method, bid evaluation device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112580299A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113506158A (en) * | 2021-09-10 | 2021-10-15 | 深圳平安综合金融服务有限公司 | Bidding method, medium and computer equipment |
| CN114595661A (en) * | 2022-05-07 | 2022-06-07 | 深圳平安综合金融服务有限公司 | Method, apparatus, and medium for reviewing bid document |
| CN115062148A (en) * | 2022-06-23 | 2022-09-16 | 广东国义信息科技有限公司 | Database-based risk control method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110307245A1 (en) * | 2010-06-14 | 2011-12-15 | Xerox Corporation | Word alignment method and system for improved vocabulary coverage in statistical machine translation |
| CN107992470A (en) * | 2017-11-08 | 2018-05-04 | 中国科学院计算机网络信息中心 | A kind of text duplicate checking method and system based on similarity |
| CN109359183A (en) * | 2018-10-11 | 2019-02-19 | 南京中孚信息技术有限公司 | The duplicate checking method, apparatus and electronic equipment of text information |
| CN109697287A (en) * | 2018-12-20 | 2019-04-30 | 龙马智芯（珠海横琴）科技有限公司 | Sentence-level bilingual alignment method and system |
| CN109710950A (en) * | 2018-12-20 | 2019-05-03 | 龙马智芯（珠海横琴）科技有限公司 | Bilingual alignment method, apparatus and system |
| CN110210952A (en) * | 2019-06-13 | 2019-09-06 | 讯飞智元信息科技有限公司 | A kind of tender Evaluation Method and device |
| CN111985208A (en) * | 2020-08-18 | 2020-11-24 | 沈阳东软智能医疗科技研究院有限公司 | Method, device and equipment for realizing punctuation mark filling |
-
2020
- 2020-12-30 CN CN202011615092.6A patent/CN112580299A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110307245A1 (en) * | 2010-06-14 | 2011-12-15 | Xerox Corporation | Word alignment method and system for improved vocabulary coverage in statistical machine translation |
| CN107992470A (en) * | 2017-11-08 | 2018-05-04 | 中国科学院计算机网络信息中心 | A kind of text duplicate checking method and system based on similarity |
| CN109359183A (en) * | 2018-10-11 | 2019-02-19 | 南京中孚信息技术有限公司 | The duplicate checking method, apparatus and electronic equipment of text information |
| CN109697287A (en) * | 2018-12-20 | 2019-04-30 | 龙马智芯（珠海横琴）科技有限公司 | Sentence-level bilingual alignment method and system |
| CN109710950A (en) * | 2018-12-20 | 2019-05-03 | 龙马智芯（珠海横琴）科技有限公司 | Bilingual alignment method, apparatus and system |
| CN110210952A (en) * | 2019-06-13 | 2019-09-06 | 讯飞智元信息科技有限公司 | A kind of tender Evaluation Method and device |
| CN111985208A (en) * | 2020-08-18 | 2020-11-24 | 沈阳东软智能医疗科技研究院有限公司 | Method, device and equipment for realizing punctuation mark filling |
Non-Patent Citations (1)
| Title |
|---|
| 郝伟博士: ""论文查重：利用Python查找两个Word文件的相同内容"", pages 1 - 6, Retrieved from the Internet <URL:《https://blog.csdn.net/weixin_43145361/article/details/103798581》> * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113506158A (en) * | 2021-09-10 | 2021-10-15 | 深圳平安综合金融服务有限公司 | Bidding method, medium and computer equipment |
| CN114595661A (en) * | 2022-05-07 | 2022-06-07 | 深圳平安综合金融服务有限公司 | Method, apparatus, and medium for reviewing bid document |
| CN115062148A (en) * | 2022-06-23 | 2022-09-16 | 广东国义信息科技有限公司 | Database-based risk control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112580299A (en) | Intelligent bid evaluation method, bid evaluation device and computer storage medium | |
| CN107247707B (en) | Enterprise association relation information extraction method and device based on completion strategy | |
| US11556703B2 (en) | Table detection in spreadsheet | |
| CN109522412B (en) | Text emotion analysis method, device and medium | |
| CN109858626B (en) | Knowledge base construction method and device | |
| CN113495900A (en) | Method and device for acquiring structured query language sentences based on natural language | |
| WO2022033426A1 (en) | Document processing method, document processing apparatus, and electronic device | |
| CN115310443A (en) | Model training method, information classification method, device, equipment and storage medium | |
| CN111782793A (en) | Intelligent customer service processing method, system and equipment | |
| CN112149680A (en) | Wrong word detection and identification method and device, electronic equipment and storage medium | |
| CN115086182A (en) | Mail recognition model optimization method and device, electronic equipment and storage medium | |
| US20210350090A1 (en) | Text to visualization | |
| CN113205046B (en) | Method, system, device and medium for identifying books | |
| US11809804B2 (en) | Text formatter | |
| KR102282025B1 (en) | Method for automatically sorting documents and extracting characters by using computer | |
| CN114330359A (en) | Semantic recognition method and device and electronic equipment | |
| JP2009053743A (en) | Document similarity derivation apparatus, document similarity derivation method and document similarity derivation program | |
| CN114416914B (en) | Processing method based on picture question and answer | |
| CN116225956A (en) | Automated testing method, apparatus, computer device and storage medium | |
| CN116150376A (en) | Sample data distribution optimization method, device and storage medium | |
| WO2023038722A1 (en) | Entry detection and recognition for custom forms | |
| CN115017385A (en) | Article searching method, device, equipment and storage medium | |
| CN112685540A (en) | Search method, search device, storage medium and terminal | |
| CN113971581A (en) | Robot control method and device, terminal equipment and storage medium | |
| CN112905752A (en) | Intelligent interaction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |