Intelligent bid evaluation method, bid evaluation equipment and computer storage medium

Through intelligent bid evaluation methods and equipment automated processing of element information in bidding and bid texts, the problem of inefficient manual review is solved, and a more efficient and accurate bid evaluation process is achieved.

CN112580299BActive Publication Date: 2024-12-03ANHUI IFLYTEK INTELLIGENT SYST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011615092.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-30
Publication Date
2024-12-03
Estimated Expiration
2040-12-30

AI Technical Summary

Technical Problem

During the existing bidding process, the compliance issues between the bidding documents and the bidding documents are manually reviewed, resulting in inefficiency and prone to missed and misrated evaluations.

Method used

Provide an intelligent bid evaluation method and equipment, which automatically finds and compares the information between the two by obtaining and processing the element information in the bidding text and bidding text, realizes automatic compliance judgment and avoids manual errors.

Benefits of technology

It improves the efficiency and accuracy of bid evaluation, reduces the phenomenon of missed and misrated evaluation, and simplifies the bid evaluation work process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112580299B_ABST
    Figure CN112580299B_ABST
Patent Text Reader

Abstract

The present application discloses an intelligent bid evaluation method, bid evaluation equipment and computer storage medium, the intelligent bid evaluation method comprising: obtaining a first element in a first text; searching for first element information of the first element in the first text, and searching for second element information of the first element in a 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 a bidding text and a tender text, and the second text is the other of the bidding text and the tender text. The intelligent bid evaluation method provided by the present application can simplify the bid evaluation work and improve the efficiency and accuracy of bid evaluation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of text processing, and in particular to an intelligent bid evaluation method, bid evaluation equipment and computer storage medium. Background Art

[0002] Tendering is a common transaction method in current domestic and foreign trade, and is widely used in bulk material procurement and other businesses. In this transaction method, the purchaser generally issues the tender documents as the tenderer. The tender documents generally contain information such as technical parameter requirements, quality requirements, after-sales service requirements, and completion date requirements of the procurement project. Then the bidder participates in the bidding competition by providing the tender documents. Finally, the tenderer forms a bid evaluation committee composed of industry experts to review the bidder's qualification documents to determine whether the bidder is qualified to bid, and to review the compliance between the bidder's bid documents and the tender documents, so as to select qualified bidders as candidate units. Finally, the bid evaluation committee scores according to the bid evaluation rules to select the winning bidder from the candidate units.

[0003] At present, in the process of reviewing the conformity between the bidding documents and the bidding documents, only manual work is involved throughout the process, which not only consumes a lot of manpower, but is also inefficient and easily leads to missed evaluations, wrong evaluations, etc. Summary of the invention

[0004] The main technical problem solved by this application is to provide an intelligent bid evaluation method, bid evaluation equipment and computer storage medium, which can simplify the bid evaluation work and improve the efficiency and accuracy of bid evaluation.

[0005] To solve the above technical problems, a technical solution adopted in the present application is: to provide an intelligent bid evaluation method, the method comprising: obtaining a first element in a first text; searching for first element information of the first element in the first text, and searching for second element information of the first element in a 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 a bidding text and a bid text, and the second text is the other of the bidding text and the bid text.

[0006] To solve the above technical problems, another technical solution adopted in the present application is: to provide a bid evaluation device, including a processor, a memory and a communication circuit, wherein the processor is coupled to the memory and the communication circuit respectively, and the processor controls itself and the memory and the communication circuit when working to implement the steps in the above method.

[0007] In order to solve the above technical problem, another technical solution adopted by the present application is: providing a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program can be executed by a processor to implement the steps in the above method.

[0008] The beneficial effect of the present application is that the present application can automatically search for the element information of the first element in the tender text and the bid text, and perform the same processing on the two element information at the same time. On the one hand, it is convenient for users to quickly and accurately judge the conformity between the bid text and the tender text. On the other hand, it can avoid the phenomenon of missed evaluation and wrong evaluation due to manual search, thereby simplifying the bid evaluation work and improving the efficiency and accuracy of bid evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0010] Figure 1 It is a flowchart of an implementation method of the intelligent bid evaluation method of this application;

[0011] Figure 2 It is a flowchart of another implementation method of the intelligent bid evaluation method of the present application;

[0012] Figure 3 It is a flowchart of another implementation method of the intelligent bid evaluation method of the present application;

[0013] Figure 4 It is a flowchart of another implementation method of the intelligent bid evaluation method of the present application;

[0014] Figure 5 It is a structural schematic diagram of an implementation method of the bid evaluation equipment of this application;

[0015] Figure 6 It is a structural schematic diagram of an implementation method of a computer storage medium of the present application. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. 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 creative work are within the scope of protection of this application.

[0017] First of all, it should be noted that the intelligent bid evaluation method in the present application is executed by a bid evaluation device, which can be any device with information processing capabilities, such as a mobile phone, a desktop computer, a laptop computer, etc., and is not limited here.

[0018] See also Figure 1 , Figure 1 It is a flow chart of an implementation method of the intelligent bid evaluation method of the present application, and the intelligent bid evaluation method includes:

[0019] S110: Acquire a first element in the first text.

[0020] Specifically, after receiving the element input by the user, the same element may be searched in the first text 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.

[0021] The first text is one of the bidding text and the tender text, that is, the first text is the bidding text or the tender text, wherein the bidding text refers to the text issued by the purchaser as the bidding party, including the various products to be purchased and the models and quantities of the various products, etc. The tender text refers to the text made by the bidder in response to the tender text in order to participate in the bidding competition, which includes the various products that the bidder can provide and the models and quantities of the various products, etc. Generally speaking, the tender text is modified based on the bidding text.

[0022] The first element refers to the product in the first text. For example, for the text "Processor configuration Intel Core I7 eighth-generation processor; memory: 8G and hard disk: 256G-SSD solid-state hard disk. 6 USB ports, of which 4 are USB 3.0", the first elements include "processor", "memory", "hard disk", "USB port" and "USB 3.0". It should be noted that the first element does not only refer to physical products, but can also be a service, a technology, etc.

[0023] S120: searching for first element information of the first element in the first text, and searching for second element information of the first element in the second text.

[0024] Specifically, the second text is the other of the tender text and the bid text, that is, when the first text is the tender text, the second text is the bid text, and when the first text is the bid text, the second text is the tender text.

[0025] Among them, the first element information refers to the descriptive information related to the first element, such as quantity, specifications, performance, etc.

[0026] The second element information refers to the descriptive information related to the element in the second text that is the same as the first element. Specifically, since the bidding document is usually modified on the basis of the tender document, the two usually include the same elements.

[0027] S130: Perform the same processing on the first element information and the second element information simultaneously.

[0028] 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 the operation instruction input by the corresponding user, etc.

[0029] The first element information and the second element information are processed identically at one moment, so that the first element information and the second element information in the first text present the same effect to the user.

[0030] In one application scenario, step S110 specifically includes: highlighting the first element information and the second element information at the same time. Highlighting the first element information and the second element information can make the first element information and the second element information more eye-catching, so that the user can quickly and accurately judge the conformity between the tender text and the bid text. Among them, the way to highlight the first element information and the second element information is: displaying the first element information and the second element information in the first text and the second text respectively in a highlighted, underlined or bolded manner, or popping up a pop-up window including the first element information and the second element information, or displaying the first element information and the second element information in a separate paragraph. In short, as long as the first element information and the second element information are made more eye-catching, the specific method is not limited.

[0031] In other application scenarios, step S110 may also be: according to the operation instruction input by the user, the first element information and the second element information are simultaneously subjected to the operation processing corresponding to the operation instruction. Specifically, at this time, the user will also input the operation instruction, for example, to underline a certain element, etc. After receiving the operation instruction input by the user, the operation processing corresponding to the operation instruction will be performed on the first element information, and the operation processing corresponding to the operation instruction will also be performed on the second element information, and the two operation processings are performed simultaneously.

[0032] From the above content, it can be seen that the present embodiment can automatically find the element information of the first element in the tender text and the bid text, and perform the same processing on the two element information at the same time. On the one hand, it is convenient for users to quickly and accurately judge the conformity between the bid text and the tender text. On the other hand, it can avoid the phenomenon of missed evaluation and wrong evaluation due to manual search, thereby simplifying the bid evaluation work and improving the efficiency and accuracy of the bid evaluation.

[0033] See also Figure 2 , Figure 2 It is a flow chart of another implementation method of the intelligent bid evaluation method of the present application, which includes:

[0034] S210: Determine the first sentence currently located by the user in the first text.

[0035] Specifically, when the user locates a sentence in the first text, it indicates that the user wants to view related elements in the located sentence.

[0036] The first sentence currently located by the user in the first text may refer to the sentence where the character currently selected by the user is located, or may refer to the sentence where the cursor of the bid evaluation 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 may be determined as the first sentence currently located in the first text, or the sentence where the cursor of the bid evaluation device is located may be determined as the first sentence currently located in the first text. How to determine the sentence located by the user is not limited in this application.

[0037] The first sentence located may be a sentence ending with a period, a comma, a semicolon or a colon, and is not limited here.

[0038] S220: Perform element recognition and entity information recognition on the first sentence to obtain a first element and entity information of the first element in the first text.

[0039] Specifically, after performing element recognition on the first sentence, the element in the first sentence is obtained, that is, the first element in the first text; after performing entity information recognition on the first sentence, the entity information in the first sentence is obtained, that is, the entity information of the first element.

[0040] The entity information includes at least one of a brand name, an item model, and a quantitative index, wherein the quantitative index refers to at least one of the number and size of the items.

[0041] Here, a pre-established database may be used to perform element recognition and entity information recognition on the first sentence, or a pre-trained recognition model may be used to perform element recognition and entity information recognition on the first sentence.

[0042] In one application scenario, in order to improve the processing speed, a naming recognition model is pre-trained to simultaneously perform element recognition and entity information recognition on the first sentence. Specifically, the first sentence is input into the pre-trained naming recognition model for recognition, and the first element in the first text and the entity information of the first element are obtained. The naming recognition model is pre-trained based on deep learning, and it can recognize the elements in the received sentence and the entity information of the element. Specifically, after the first sentence is input into the naming recognition model, the naming recognition model outputs the first element and the entity information of the first element in correspondence. For example, after the sentence "Processor configuration Intel Core I7 eighth generation processor" is input into the pre-trained naming recognition model, the content output by the naming recognition model is: the brand name of the processor is Intel, and the model of the processor is Core I7 eighth generation.

[0043] It is understandable that when there is no entity information in the input sentence, the naming recognition model will only output the elements in the sentence. For example, after the sentence "Memory: 8G and Hard Drive: 256G-SSD Solid State Drive" is input into the naming recognition model, the output of the naming recognition model is: memory, hard drive.

[0044] It should be noted that, in other implementations, the elements and entity information in the first sentence may also be identified respectively by two different models.

[0045] S230: Performing element value recognition on the first sentence according to the first element to obtain the element value of the first element in the first text.

[0046] Specifically, the element value of the first element refers to information that directly describes the first element, that is, identifying the element value of the first sentence according to the first element refers to searching for information that directly describes the first element in the first sentence. It can be understood that the element value of the first element includes entity information of the first element.

[0047] In one application scenario, in order to improve processing speed, a reading comprehension model is pre-trained to identify element values ​​of a first sentence. Specifically, the first sentence and the first element are input into the pre-trained reading comprehension model for identification to obtain the element value of the first element in the first text.

[0048] Among them, the reading comprehension model is also pre-trained based on deep learning. Its input is the element name and related sentences, and its output is the element value corresponding to the element name. The output element value can be a single value or a combination of multiple values. That is to say, when there are multiple element values ​​corresponding to the same element in the input sentence, the reading comprehension model can output all the multiple element values.

[0049] Among them, a sentence and multiple elements in the sentence can be input into the reading comprehension model, and then the reading comprehension model outputs the element values ​​of the multiple elements accordingly. For example, for the sentence "Processor configuration Intel Core I7 eighth-generation processor; memory: 8G and hard disk: 256G-SSD solid-state hard disk. There are 6 USB ports, of which 4 are USB 3.0", after identifying that it includes the five elements of processor, memory, hard disk, USB port and USB 3.0 in step S220, the sentence and the five elements are input into the reading comprehension model for identification, and the element value of the processor element is Intel Core I7 eighth-generation processor, the element value of the memory element is 8G, the element value of the hard disk element is 256G-SSD solid-state hard disk, the element value of the USB port element is 6, and the element value of the USB 3.0 element is 4. The specific corresponding relationship can be seen in the following Table 1:

[0050] Table 1 Correspondence between element names and element values

[0051]

[0052] During recognition, the first sentence and the first element may be input into the reading comprehension 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 comprehension model.

[0053] S240: Searching for a second sentence aligned with the first sentence in the second text.

[0054] Specifically, the alignment of the first sentence with the second sentence 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. Considering that the bidding documents are usually revised based on the tender documents, an obvious feature of the two texts is that the two texts maintain a consistent order in the description of elements. Therefore, the two sentences in the same position in the first text and the second text may describe the same elements.

[0055] Among them, the sentence sequence number of the first sentence in the first text can be first searched, and then the second sentence aligned with the first sentence can be searched in the second text according to the sentence sequence number, wherein the sentence sequence number represents the sentence number of the first sentence in the first text. For example, if the sentence sequence number of the first sentence is 5 (that is, the first sentence is the 5th sentence in the first text), the 5th sentence is searched in the second text, and the sentence found is the second sentence. When judging the sentence sequence numbers in the first text and the second text, a sentence ending with a preset punctuation mark is considered as one sentence. For example, if the preset punctuation mark is a period, then a sentence ending with a period in both the first text and the second text is considered as one sentence.

[0056] S250: Perform element recognition and entity information recognition on the second sentence to obtain a second element corresponding to the first element in the second text and entity information of the second element.

[0057] Specifically, this process is similar to step S220. For details, please refer to the above content and will not be repeated here.

[0058] S260: Performing element value recognition on the second sentence according to the second element to obtain the element value of the second element in the second text.

[0059] Specifically, this process is similar to step S230. For details, please refer to the above content and will not be repeated here.

[0060] S270: Perform the same processing on the first element information including the entity information of the first element and the element value and the second element information including the entity information of the second element and the element value at the same time.

[0061] Specifically, the element information in this embodiment includes element value and entity information, so when processing, the entity information and element value of the first element and the entity information and element value of the second element are processed simultaneously.

[0062] It should be noted that when the processing in step S270 refers to highlighting, the element value includes entity information, and the purpose of displaying both the entity information and the element value is to highlight the entity information.

[0063] When the first element information and the second element information are highlighted, the first element and the second element can be highlighted at the same time, for example, a pop-up window is popped up to display the first element and the first element information, as well as the second element and the second element information, and when displayed, the first element and the first element information are displayed correspondingly, and the second element and the second element information are displayed correspondingly.

[0064] It should be noted that although the above-mentioned solution of the present application is described with steps S210 to S270, it does not mean that the solution in the present application must be executed in the order of steps S210 to S270. In other words, the technical solution of the present application can disrupt the above order. For example, step S230 can be executed after step S240 or step S250.

[0065] At the same time, when the above implementation method recognizes the first sentence and the second sentence, the pre-trained naming recognition model and reading comprehension model are used to avoid wrong evaluation and missed evaluation during manual review.

[0066] In other implementations, step S260 may be replaced by: 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. This can avoid the situation where the element value is identified even though there is no first element in the second sentence.

[0067] See also Figure 3 , Figure 3 It is a flow chart of another implementation method of the intelligent bid evaluation method of the present application, which includes:

[0068] S301: Check and correct the formats of the first text and the second text respectively.

[0069] Specifically, considering that the tendering party cannot strictly meet the standard requirements on the writing format of the bidders, some bidders are arbitrary in the writing format, use punctuation marks incorrectly, or replace punctuation marks with "spaces", "line breaks", and "TAB keys". This will increase the difficulty of distinguishing elements in the subsequent process and reduce the efficiency of the entire processing process. In order to avoid this defect, this embodiment will pre-check and correct the format of the first text and the second text, and then perform subsequent steps based on the corrected first text and the corrected second text. It should be noted that in other embodiments, if the formats of the first text and the second text can be strictly standardized, step S301 may not be performed at this time.

[0070] When format checking and correcting, corrections can be made according to a preset strategy, which specifies what kind of errors should be corrected. For example, the preset strategy is to replace all spaces in the text with null characters.

[0071] In an application scenario, in order to improve the processing speed and the accuracy of correction, a pre-trained punctuation error detection model is used to check and correct the format of the first text and the second text respectively. The punctuation error detection model is pre-trained. 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 relatively standardized format can be collected as training data for the model. At the same time, in order to ensure the accuracy of the training data to further improve the error detection effect of the final model, the punctuation and sentence segmentation in the training data can also be manually corrected, and finally training is performed based on the corrected data.

[0072] In one application scenario, in order to reduce the recognition difficulty of the punctuation error detection model and make the final correction effect more accurate, the punctuation error detection model retains the punctuation marks in the original text when checking and correcting the format of the first text and the second text respectively, and only predicts the positions where there are no punctuation marks. In this way, the contextual punctuation information can be fully utilized in the recognition process to improve the accuracy of the final correction. For example, for "spaces", "line breaks", "TAB keys", etc. in the first text or the second text, the punctuation error detection model will consider in which cases they are used instead of punctuation marks and in which cases they do not represent any meaning. If they are used instead of punctuation marks, punctuation marks are added to the corresponding positions. If they do not represent any meaning, space characters are added to the corresponding positions.

[0073] In one application scenario, the predicted label of the punctuation error detection model includes at least one of a colon, a comma, a period, a line break, and a space character. The space character means that no punctuation should be added at the current position, and the line break character is used at the end of each element to start a new line.

[0074] For example, when the predicted labels of the punctuation detection model include colon, comma, period, line break and space character, the punctuation detection model will predict whether the position should be a colon, comma, period, line break or space character when predicting a position without punctuation marks. If the position is not one of the colon, comma, period, line break and space character, no correction will be made. If it is one of the colon, comma, period, line break and space character, then the correction will be made accordingly.

[0075] Referring to Table 2 below, after the following original text is input into the punctuation error detection model, the punctuation error detection model outputs the checked and corrected text.

[0076] Table 2 Comparison between original text and text after error detection

[0077]

[0078] It can be understood that after step S301, the first text and the second text are already files in a standard format, and then subsequent steps are performed based on the corrected first text and the second text.

[0079] S302: Perform 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.

[0080] Specifically, the process of word segmentation is to split a sentence into several words, wherein the sentence here refers to a sentence ending with a period, a comma, a semicolon or a colon.

[0081] The word segmentation process may be based on a dictionary word segmentation algorithm or a statistical machine learning algorithm, and there is no limitation here.

[0082] After word segmentation, a first word sequence corresponding to the first text and a second word sequence corresponding to the second text are obtained.

[0083] S303: Record the mapping relationship between each sentence in the first text, each sentence in the second text and the words included therein respectively.

[0084] 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.

[0085] In an application scenario, the correspondence between a sentence and the words included in it is recorded through the starting position of the words corresponding to the sentence. Specifically, the words in the first word sequence and the second word sequence are sorted according to the order in the first text and the second text, and then the words in the first word sequence and the second word sequence are numbered starting from 0, and then for each sentence in the first text and the second text, the number of the first word and the number of the last word included in each are recorded. Then, for a sentence in the first text or the second text, according to the number of the recorded first word and the number of the last word, it is possible to find several words included in the corresponding sequence, thereby realizing the mapping relationship between the recorded sentences and words.

[0086] S304: Align the words in the first word sequence with the words in the second word sequence.

[0087] Specifically, aligning the words in the first word sequence with the words in the second word sequence refers to matching the same or similar words in the first word sequence and the second word sequence, and establishing a corresponding matching relationship.

[0088] In an application scenario, considering that the bidding text is usually modified based on the tender text, it has an obvious feature that the two are basically consistent in terms of element description. Based on this, this implementation uses the minimum edit distance algorithm to align the words in the first word sequence with the words in the second word sequence. Specifically, during the processing, 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 the least addition, deletion, and modification operations. Among them, when using the minimum edit distance algorithm for processing, the operations involved include deleting a word, inserting a word, and replacing a word.

[0089] In this application scenario, the minimum edit distance algorithm is used to align the words in the first word sequence with the words in the second word sequence. Even if there are many similar words in the first word sequence and the second word sequence, incorrect alignment is not likely to occur.

[0090] In other application scenarios, the words in the first word sequence and the second word sequence may also be aligned according to the similarity between the words.

[0091] S305: According to the mapping relationship between each sentence in the first text, each sentence in the second text and the words included therein, the alignment relationship between the words in the first word sequence and the words in the second word sequence is converted into an alignment relationship between the sentences in the first text and the sentences in the second text, so as to align the sentences in the first text with the sentences in the second text.

[0092] Specifically, after aligning the words in the first word sequence with the words in the second word sequence, the alignment relationship between the words can be converted into an alignment relationship between sentences according to the previously recorded mapping relationship, so as to align the sentences in the first text with the sentences in the second text. After the sentence alignment is achieved, there may be a one-to-one situation or a one-to-many situation, wherein the one-to-one situation refers to the alignment of one sentence with one sentence, and the one-to-many situation refers to the alignment of one sentence with more than two sentences (the two or more sentences describe the same element).

[0093] For example, in Table 3 below, after alignment, a corresponding relationship is established between the sentences in the first text and the sentences in the second text.

[0094] Table 3 Correspondence between the first text and the second text after alignment

[0095]

[0096]

[0097] Among them, in Table 3 above, the "built-in wired network card and wireless network card are required" in the first text does not have similar content in the second text, so there is no corresponding sentence to align with it.

[0098] S306: Determine the first sentence currently located by the user in the first text.

[0099] S307: Perform element recognition and entity information recognition on the first sentence to obtain a first element and entity information of the first element in the first text.

[0100] S308: Performing element value recognition on the first sentence according to the first element to obtain the element value of the first element in the first text.

[0101] S309: Searching for a second sentence aligned with the first sentence in the second text.

[0102] S310: Perform element recognition and entity information recognition on the second sentence to obtain a second element corresponding to the first element in the second text and entity information of the second element.

[0103] S311: Performing element value recognition on the second sentence according to the second element to obtain the element value of the second element in the second text.

[0104] S312: Perform the same processing on the first element information including the entity information of the first element and the element value and the second element information including the entity information of the second element and the element value at the same time.

[0105] The contents of step S306 to step S312 are the same as the contents of step S210 to step S270 in the above embodiment. For details, please refer to the above embodiment and will not be repeated here.

[0106] In this embodiment, the format of the first text and the second text are checked and corrected in advance, and the sentences in the first text and the sentences in the second text are aligned, so that the first text and the second text are clearer in structure, providing favorable conditions for subsequent processing, thereby improving the processing speed of bid evaluation.

[0107] At the same time, in this embodiment, after the first text and the second text are checked and corrected, during the bid evaluation process, the corrected first text and the second text can be directly displayed to the user for user reading convenience.

[0108] See also Figure 4 , Figure 4 It is a flow chart of another implementation method of the intelligent bid evaluation method of the present application, which includes:

[0109] S410: Determine the first sentence currently located by the user in the first text.

[0110] S420: Perform element recognition on the first sentence to obtain a first element in the first text.

[0111] S430: Performing element value recognition on the first sentence according to the first element to obtain the element value of the first element in the first text.

[0112] S440: Searching for a second sentence aligned with the first sentence in the second text.

[0113] S450: Performing element value recognition on the second sentence according to the first element to obtain the element value of the first element in the second text.

[0114] S460: Perform the same processing on the element value in the first text and the element value in the second text at the same time.

[0115] Different from the above-mentioned implementation mode, on the one hand, the first element information and the second element information only include element values, and on the other hand, when obtaining the element value of the first element in the second text, the second sentence will be identified based on the first element, without the need to identify the second element in the second sentence. This can avoid the situation where there is no first element in the second sentence at all (an error occurs during alignment, the first sentence and the second sentence are aligned, but the two do not describe the same element), but the element value can be identified. In addition, this implementation mode can also improve the processing speed.

[0116] In other implementations, step S440 and step S450 may also be replaced by: identifying the second text according to the first element to obtain the element value of the first element in the second text. It should be noted that, although it is not necessary to find the second sentence aligned with the first sentence to improve the processing speed, there is a defect that it is not close to the user's intention, which is explained below with specific examples:

[0117] Suppose the school needs to purchase two types of desktop computers, one for teachers and the other for students. The two computers have different configurations, and there are two sentences in both the first and second texts. The first sentence describes the processor of the desktop computer for students, and the second sentence describes the processor of the desktop computer for teachers. In the process of bid evaluation, if the user (evaluator) wants to see the consistency between the two files about the desktop computers for students, suppose he selects several characters in the first sentence of the first text, and then the bid evaluation device will recognize the first sentence and obtain the element in the first sentence as the processor and the corresponding element information. If the second text is then recognized based on the processor element, the element information obtained includes both the description information of the desktop computer for students and the description information of the computer for teachers. Obviously, the final result is not what the user wants.

[0118] See also Figure 5 , Figure 5 1 is a schematic diagram of the structure 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. The processor 210 is coupled to the memory 220 and the communication circuit 230 respectively. The memory 220 stores program data. The processor 210 implements the steps of the method in any of the above embodiments by executing the program data in the memory 220. The detailed steps can be found in the above embodiments and will not be repeated here.

[0119] The bid evaluation device 200 may be any device with information processing capabilities, such as a mobile phone, a desktop computer, a laptop computer, etc., and is not limited here.

[0120] See also Figure 6 , Figure 6 The computer storage medium 300 stores a computer program 310, which can be executed by a processor to implement the steps in any of the above methods.

[0121] Among them, the computer storage medium 300 can specifically be a device that can store the computer program 310, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, or it can also be a server that stores the computer program 310. The server can send the stored computer program 310 to other devices for execution, or it can also run the stored computer program 310 by itself.

[0122] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An intelligent bid evaluation method, characterized in that: The method comprises: Acquire a first element in a first text; specifically, determine a first sentence currently located by a user in the first text; perform element recognition on the first sentence to obtain the first element in the first text; wherein the first sentence is a sentence where a character currently selected by the user is located or a sentence where a cursor of a bid evaluation device is located; Searching for first element information of the first element in the first text, and searching for second element information of the first element in the second text; specifically, the first element information and the second element information both include element values, performing element value recognition on the first sentence according to the first element, and obtaining the element value of the first element in the first text; searching for a second sentence aligned with the first sentence in the second text; performing element value recognition on the second sentence according to the first element, and obtaining the element value 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; The first text is one of a bidding text and a tender text, and the second text is the other of the bidding text and the tender text; Before the step of obtaining the first element in the first text, the method further includes: performing word segmentation processing on each sentence in the first text and each sentence in the second text to obtain a first word sequence and a second word sequence; recording the mapping relationship between each sentence in the first text and each sentence in the second text and the words included therein; aligning the words in the first word sequence with the words in the second word sequence; converting the alignment relationship between the words in the first word sequence and the words in the second word sequence into the alignment relationship between the sentences in the first text and the sentences in the second text according to the mapping relationship between the sentences in the first text and the second text and the words included therein, so as to align the sentences in the first text with the sentences in the second text; wherein, one sentence in the first text is aligned with one sentence or more than two sentences in the second text.

2. The method according to claim 1, characterized in that The first element information and the second element information both further include entity information, and the entity information includes at least one of a brand name, an item model, and a quantitative index; the method further includes: Performing entity information recognition on the first sentence to obtain entity information of the first element in the first sentence; Perform entity information recognition on the second sentence to obtain entity information of the second element in the second sentence.

3. The method according to claim 1, characterized in that Before the step of performing word segmentation processing on each sentence in the first text and each sentence in the second text, the method further includes: The formats of the first text and the second text are checked and corrected respectively.

4. The method according to claim 3, characterized in that The steps of respectively checking and correcting the format of the first text and the second text include: The pre-trained punctuation error detection model is used to perform format checking and correction on the first text and the second text respectively.

5. The method according to claim 4, characterized in that When the punctuation error detection model performs format checking and correction on the first text and the second text respectively, it predicts symbols for positions where no punctuation marks are set, wherein the predicted labels of the punctuation error detection model include at least one of a colon, a comma, a period, a line break, and a space character.

6. A bid evaluation device, characterized in that: The method comprises a processor, a memory and a communication circuit, wherein the processor is coupled to the memory and the communication circuit respectively, and the processor controls itself, the memory and the communication circuit when working to implement the steps in the method as described in any one of claims 1-5.

7. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and the computer program can be executed by a processor to implement the steps in the method according to any one of claims 1 to 5.