Bidding document generation method and device, equipment and medium

Abstract

The invention discloses a bidding document generation method and device, equipment and a medium. The method comprises the following steps: acquiring bidding document text data and bidding document background data; obtaining a screening text, wherein the screening text comprises at least one screening parameter and a screening condition corresponding to each screening parameter; identifying the screened text to obtain at least one bidding document title and at least one bidding document keyword corresponding to each bidding document title; for each bidding document title, querying in the bidding document text data according to each bidding document keyword corresponding to the bidding document title to obtain bidding document paragraph data corresponding to the bidding document title; and generating a target bidding document according to each bidding document title, the bidding document paragraph data corresponding to each bidding document title and the bidding document background data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a bid generation method, device, equipment and medium. Background Art

[0002] The company has limited human resources and a limited scope of work that can be managed, and is unable to efficiently complete a large amount of work to be done, so it conducts project bidding. Other companies write bids, and the company selects companies that meet the requirements based on the bids to assist it in completing the work.

[0003] Currently, there are many companies waiting to bid, and each company has different bidding requirements. Bids are written manually based on the bidding requirements of each company.

[0004] However, manual bidding is inefficient and difficult to complete in a timely manner. Summary of the invention

[0005] The present invention provides a bid document generation method, device, equipment and medium to improve the accuracy of bid document generation.

[0006] In a first aspect, an embodiment of the present invention provides a method for generating a bid document, the method comprising:

[0007] Obtain the tender document body data and tender document background data;

[0008] Obtaining a filtering text, the filtering text including: at least one filtering parameter and filtering conditions corresponding to each filtering parameter;

[0009] Identify the screening text to obtain at least one tender title and at least one tender keyword corresponding to each tender title;

[0010] For each bid title, according to each bid keyword corresponding to the bid title, the bid paragraph data corresponding to the bid title is searched in the bid text data;

[0011] A target bid is generated according to each bid title, bid paragraph data corresponding to each bid title and bid background data.

[0012] In a second aspect, an embodiment of the present invention further provides a bid document generation device, the device comprising:

[0013] The tender document data acquisition module is used to acquire the tender document body data and tender document background data;

[0014] A screening text acquisition module is used to acquire the screening text, the screening text includes: at least one screening parameter and the screening conditions corresponding to each screening parameter;

[0015] A text recognition module, used to recognize the screening text, and obtain at least one tender title and at least one tender keyword corresponding to each tender title;

[0016] The paragraph data acquisition module is used to query the bid document paragraph data corresponding to each bid document title in the bid document body data according to each bid document keyword corresponding to the bid document title;

[0017] The bid generation module is used to generate a target bid based on each bid title, bid paragraph data corresponding to each bid title, and bid background data.

[0018] In a third aspect, an embodiment of the present invention further provides a tender document generation device, the tender document generation device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the bid generation method of any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the bid generation method of any embodiment of the present invention when executed.

[0023] The technical solution of the embodiment of the present invention obtains the bid body data and bid background data; obtains the screening text, the screening text includes: at least one screening parameter and the screening conditions corresponding to each screening parameter; identifies the screening text to obtain at least one bid title and at least one bid keyword corresponding to each bid title; for each bid title, according to each bid keyword corresponding to the bid title, queries in the bid body data to obtain the bid paragraph data corresponding to the bid title; generates a target bid according to each bid title, the bid paragraph data corresponding to each bid title and the bid background data, and generates the bid through multi-dimensional data, thereby improving the accuracy of bid generation, and eliminating the need for manual bid writing, thereby improving the efficiency of bid generation.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 is a flowchart of a bid generation method provided according to Embodiment 1 of the present invention;

[0027] Figure 2 is a flow chart of a method for generating a tender document provided according to Embodiment 2 of the present invention;

[0028] Figure 3 is a structural diagram of a tender document generating device provided according to an embodiment of the present invention;

[0029] Figure 4 It is a structural schematic diagram of a bid document generation device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of the engine types involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0033] The information collected is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0034] Embodiment 1

[0035] Figure 1 A flowchart of a bid generation method provided in Embodiment 1 of the present invention. The embodiment of the present invention is applicable to the case of bid generation, and the method can be executed by a bid generation device, which can be implemented in the form of hardware and / or software and can be applied in the field of financial technology.

[0036] See also Figure 1 The method for generating a tender document as shown comprises:

[0037] S101, obtaining tender document body data and tender document background data.

[0038] The tender document body data may be descriptive information indicating the bidding intention, and the tender document background data may be descriptive information of the basic situation of the company or enterprise.

[0039] Specifically, a tender document is a practical document used to announce the main items and requirements of the tender to potential bidders. The main function of the tender document is to provide bidders with detailed technical, quality, construction period and other requirements. It is the basis for the tendering unit to prepare the tender document. The tendering unit must respond substantially to the content of the tender document, otherwise its bid will be deemed invalid. The tender document usually includes the following parts: Title, which is used to describe the name and nature of the tender project. The body, which is used to describe the specific content such as the background, requirements, technical specifications, quality standards and construction period of the tender project. The end, which is used to describe the necessary information such as contact information and deadline. The tender document is a text submitted by the tendering unit to the tendering unit in accordance with the conditions and requirements of the tender document to compete for the bid. The tender document generally includes the following main contents: Comprehensive description, which is used to describe the overall description of the tender project. The cost of a single project and the total cost of the project quantity, which are calculated by the project quantity to obtain the cost of a single project and the total project. The quality of the project, which is used to describe the achievable level. The construction plan, which describes the planned start and completion time, construction organization design, project image progress, prefabrication and temporary facilities arrangements, etc. Construction methods are used to describe the main construction methods and the selected construction machinery. Opinions on the bidding documents are used to describe the response to the bidding documents and the opinions put forward. The data in the body of the bid document may include: comprehensive description, cost of a single project and total cost of the project, main technical solutions, project quality, construction plan, construction methods and opinions on the bidding documents. The background data of the bid document may include: introduction to the development history of the bidding enterprise, name of the bidding enterprise, registration time, registration cost, enterprise scale, corporate culture, after-sales service and brief introduction to the enterprise's historical bidding cases, etc.

[0040] S102: Obtain a filtering text, where the filtering text includes: at least one filtering parameter and filtering conditions corresponding to each filtering parameter.

[0041] The screening text may be descriptive information for screening the bidding documents.

[0042] Specifically, a bidding selection document is a document issued by the tenderer during the bidding process to invite companies to participate in the bidding. The bidding selection document details the specific requirements, technical specifications, bidding qualifications, bidding methods and evaluation criteria of the bidding project to ensure that all bidders can compete on the same basis. An information screening model can be obtained through training with multiple historical selection documents. The model can identify bidding selection documents. The bidding company can obtain at least one bidding selection document, identify each bidding selection document through the information screening model, and obtain at least one screening parameter and the screening conditions corresponding to each screening parameter. For example, the screening parameters can be the project budget cost, project duration, project level and the registration cost of the bidding company.

[0043] S103: Identify the screening text to obtain at least one tender title and at least one tender keyword corresponding to each tender title.

[0044] The bid title may be the title of a chapter in the outline of the bid, and the bid keyword may be a word corresponding to the bid title.

[0045] Specifically, the screening text includes: at least one screening parameter and the screening conditions corresponding to each screening parameter. The bidding company generates an outline of the bid based on the screening text so that the content of the bid meets the screening conditions. The corresponding relationship between the screening parameters and the bid title is obtained, and the acquisition method can be obtained by preset by industry experts or by neural network recognition. One screening parameter can correspond to one bid title, and multiple screening parameters can correspond to one bid title. A bid title can correspond to at least one bid keyword, and the content corresponding to the bid title is data with the bid keywords corresponding to the bid title as the theme. The content corresponding to the bid title is generated around the bid keywords corresponding to the bid title, and is the description information of the bid keywords corresponding to the bid title. For example, the bid title is the project schedule, and the keywords corresponding to the bid title are: start date, completion date, construction days, vacation schedule and duty schedule, etc.

[0046] S104. For each bid title, according to each bid keyword corresponding to the bid title, the bid paragraph data corresponding to the bid title is searched in the bid text data.

[0047] The bid paragraph data may be the bid content corresponding to the bid title.

[0048] Specifically, the bid body data is equivalent to a database of bid content. The bid body data is a collection of bid section data, which includes: material keywords and content with material keywords as the theme. For each bid title, the bid keyword corresponding to the bid title is used to query in the bid body data to obtain the material keyword corresponding to the bid keyword corresponding to the bid title. The material keyword can be the same as the bid keyword or a word with similar semantics to the bid keyword. The content corresponding to the material keyword is used as the content corresponding to the bid title.

[0049] S105 , generating a target bid document according to each bid document title, bid document paragraph data corresponding to each bid document title, and bid document background data.

[0050] The target bid may be a bid generated corresponding to the screened text.

[0051] Specifically, a screening text is obtained according to the bidding selection document. At least one bid title is determined according to the screening text. The bid paragraph data corresponding to each bid title is queried in the bid body data. Different bidding selection documents correspond to different bid paragraph data. However, there is a part of the company's descriptive information in the bid of the same enterprise. This part is fixed content and does not need to change according to the content of different selection documents. This part of content is collectively referred to as bid background data. The bid background data, each bid title, and the bid paragraph data corresponding to each bid title are combined into a target bid according to the order of the screening conditions in the screening text.

[0052] The technical solution of the embodiment of the present invention obtains the bid body data and bid background data; obtains the screening text, the screening text includes: at least one screening parameter and the screening conditions corresponding to each screening parameter; identifies the screening text to obtain at least one bid title and at least one bid keyword corresponding to each bid title; for each bid title, according to each bid keyword corresponding to the bid title, queries in the bid body data to obtain the bid paragraph data corresponding to the bid title; generates a target bid according to each bid title, the bid paragraph data corresponding to each bid title and the bid background data, and generates the bid through multi-dimensional data, thereby improving the accuracy of bid generation, and eliminating the need for manual bid writing, thereby improving the efficiency of bid generation.

[0053] Embodiment 2

[0054] Figure 2 This is a flow chart of a method for generating a tender document provided in the second embodiment of the present invention. Based on the above embodiments, the embodiment of the present invention optimizes and improves the tender document generation operation.

[0055] Further, "according to each bid keyword corresponding to the bid title, query the bid body data to obtain the bid paragraph data corresponding to the bid title" is refined into "obtaining the required word count and keyword similarity requirement range for the paragraph corresponding to the bid title; for each bid keyword corresponding to the bid title, determining at least one similar keyword corresponding to the bid keyword according to the keyword similarity requirement range corresponding to the bid title; according to each similar keyword corresponding to the bid title, query the bid body data to obtain the initial paragraph data corresponding to the bid title; according to the required word count of the paragraph corresponding to the bid title, filter the initial paragraph data corresponding to the bid title to obtain the bid paragraph data corresponding to the bid title" to improve the bid generation operation.

[0056] It should be noted that for the parts not described in detail in the embodiments of the present invention, reference may be made to the descriptions of other embodiments.

[0057] See also Figure 2 The tender document generation method shown includes:

[0058] S201, obtaining the tender document body data and tender document background data.

[0059] S202: Obtain a filtering text, where the filtering text includes: at least one filtering parameter and filtering conditions corresponding to each filtering parameter.

[0060] S203: Identify the filtered text to obtain at least one tender title and at least one tender keyword corresponding to each tender title.

[0061] S204, obtaining the required word count of the paragraph corresponding to the bid title and the required range of keyword similarity.

[0062] The required number of words in a paragraph may be the number of words in the bid document paragraph data corresponding to the preset bid document title. The keyword similarity requirement range may be used to describe the range of similarity values ​​that may be similar to the bid document keyword.

[0063] Specifically, the writing requirements of the tender can be determined based on the filtered text. The writing requirements of the tender can also be obtained based on the rules customized by the enterprise. At the same time, different users can also preset writing requirements. Based on the above, the required number of words and keyword similarity requirements for each paragraph corresponding to the title of the tender can be determined.

[0064] S205 . For each bid keyword corresponding to the bid title, determine at least one similar keyword corresponding to the bid keyword according to a keyword similarity requirement range corresponding to the bid title.

[0065] Among them, similar keywords can be words similar to the keywords in the bid document.

[0066] Specifically, a bid title corresponds to at least one bid keyword. The content of each bid keyword can be expanded. For a bid keyword, at least one similar keyword can be generated. By adding keywords corresponding to the bid title, more multi-dimensional content can be obtained, and the comprehensiveness of the bid paragraph data can be improved. The larger the similarity requirement range, the more keywords need to be expanded for the bid keywords, and the more diversified the content of the generated bid paragraph data. The smaller the similarity requirement range, the fewer keywords need to be expanded for the bid keywords, and the content of the generated bid paragraph data only revolves around the bid keywords.

[0067] S206. According to the similar keywords corresponding to the bid title, the initial paragraph data corresponding to the bid title is searched in the bid body data.

[0068] The initial paragraph data may be the bid document paragraph data retrieved based on similar keywords corresponding to the bid document title.

[0069] Specifically, a bid title corresponds to at least one bid keyword. A bid keyword corresponds to at least one similar keyword. According to each similar keyword, a query is performed in the bid body data to obtain the content corresponding to each similar keyword, and the content corresponding to each similar keyword is integrated to obtain the initial paragraph data corresponding to the bid title.

[0070] S207 , screening the initial paragraph data corresponding to the bid title according to the required number of words of the paragraph corresponding to the bid title, and obtaining the bid paragraph data corresponding to the bid title.

[0071] Specifically, at least one preset editing mode may be obtained, and the preset editing mode may be to expand or delete a sentence. The required number of words of the paragraph corresponding to the tender document title is compared with the initial paragraph data corresponding to the tender document title to determine whether the initial paragraph data corresponding to the tender document title needs to be expanded or deleted. According to the judgment, the corresponding preset editing mode is executed to filter the initial paragraph data corresponding to the tender document title to obtain the tender document paragraph data corresponding to the tender document title.

[0072] S208, generating a target bid document according to each bid document title, bid document paragraph data corresponding to each bid document title, and bid document background data.

[0073] The embodiment of the present invention obtains the required word count of a paragraph and the keyword similarity requirement range corresponding to the tender title; for each tender keyword corresponding to the tender title, determines at least one similar keyword corresponding to the tender keyword according to the keyword similarity requirement range corresponding to the tender title; according to each similar keyword corresponding to the tender title, queries the tender body data to obtain initial paragraph data corresponding to the tender title; according to the required word count of the paragraph corresponding to the tender title, filters the initial paragraph data corresponding to the tender title to obtain the tender paragraph data corresponding to the tender title, and can perform different operations according to different user needs, thereby refining the steps of tender generation and improving the accuracy of tender generation.

[0074] Optionally, determining at least one similar keyword corresponding to a bid keyword based on a keyword similarity requirement range corresponding to the bid title includes: obtaining at least one keyword set, the keyword set including: bid keywords, candidate keywords and similarity values ​​between the bid keywords and the candidate keywords; determining at least one target set in each keyword set based on the similarity values ​​between the bid keywords and the candidate keywords in each keyword set and the keyword similarity requirement range; determining at least one similar keyword corresponding to the bid keyword based on the candidate keywords in each target set.

[0075] The keyword set may be a set of description information of preset keywords. The candidate keywords may be texts similar to the bid keywords. The target set may be a set of keywords whose similarity values ​​between the bid keywords and the candidate keywords are within the keyword similarity requirement range.

[0076] Specifically, at least one keyword set is obtained, and the keyword set includes: bid keywords, candidate keywords, and similarity values ​​between the bid keywords and the candidate keywords. The keyword set can be preset by industry experts. Based on the comparison between the similarity values ​​between the bid keywords and the candidate keywords in each keyword set and the keyword similarity requirement range, the keyword set whose similarity values ​​between the bid keywords and the candidate keywords are within the keyword similarity requirement range is determined as the target set. Based on each target set, the candidate keywords in each target set are determined as at least one similar keyword corresponding to the bid keyword.

[0077] By obtaining at least one keyword set, the keyword set includes: bid keywords, candidate keywords and similarity values ​​between the bid keywords and the candidate keywords; determining at least one target set in each keyword set according to the similarity values ​​between the bid keywords and the candidate keywords in each keyword set and the keyword similarity requirement range; determining at least one similar keyword corresponding to the bid keyword according to the candidate keywords in each target set, expanding different bid keywords to different ranges, and obtaining different numbers of similar keywords for different bid keywords, the accuracy of bid generation is improved.

[0078] Optionally, based on similar keywords corresponding to the tender title, initial paragraph data corresponding to the tender title is queried in the tender body data, including: obtaining a text weight set, the text weight set including: at least one tender word and the expected weight corresponding to each tender word; based on similar keywords corresponding to the tender title, the text weight set is queried to obtain the expected weight corresponding to each similar keyword; the content query order is determined based on the expected weight corresponding to each similar keyword; and the initial paragraph data corresponding to the tender title is queried in the tender body data based on the content query order.

[0079] The text weight set may be a set of weight description information of keywords. The bid words may be bid keywords corresponding to preset bid titles. The expected weight may be the weight corresponding to the bid words. The content query order may be the query order of the bid keywords corresponding to the bid titles.

[0080] Specifically, a text weight set is obtained, and the text weight set includes: at least one bid word and the expected weight corresponding to each bid word. Historical bids within a historical time period are obtained, and the contents of the historical bids are divided according to the content with the highest repetition rate and the keywords corresponding to different repetition rates are determined, and the weight corresponding to each keyword is determined according to the repetition rate of each keyword. According to each similar keyword corresponding to the bid title, the expected weight corresponding to each similar keyword is queried in the text weight set; the content query order is determined according to the expected weight corresponding to each similar keyword; according to the content query order, the initial paragraph data corresponding to the bid title is queried in the bid body data to obtain the initial paragraph data, and the higher the expected weight, the more content involving the expected weight in the initial paragraph data, and the lower the expected weight, the less content involving the expected weight in the initial paragraph data.

[0081] By obtaining a text weight set, the text weight set includes: at least one bid word and the expected weight corresponding to each bid word; according to each similar keyword corresponding to the bid title, querying in the text weight set to obtain the expected weight corresponding to each similar keyword; determining the content query order according to the expected weight corresponding to each similar keyword; according to the content query order, querying in the bid body data to obtain the initial paragraph data corresponding to the bid title, and generating content corresponding to the bid title according to different expected weights, and the generated content is more accurate.

[0082] Optionally, initial paragraph data corresponding to the bid title is screened according to the required number of words for the paragraph corresponding to the bid title to obtain bid paragraph data corresponding to the bid title, including: obtaining the initial number of words in the initial paragraph data corresponding to the bid title; comparing the initial number of words with the required number of words for the paragraph to obtain a word count comparison result; modifying the initial paragraph data corresponding to the bid title according to the word count comparison result to obtain bid paragraph data corresponding to the bid title.

[0083] The initial word count may be the word count of the initial paragraph data corresponding to the bid title, and the word count comparison result may be the result of comparing the initial word count with the required word count of the paragraph.

[0084] Specifically, the initial word count of the initial paragraph data corresponding to the bid title is obtained, and the initial word count is compared with the required word count of the paragraph to obtain a word count comparison result. If the word count comparison result is that the initial word count is greater than the required word count of the paragraph, the initial paragraph data needs to be deleted. If the word count comparison result is that the initial word count is less than the required word count of the paragraph, the initial paragraph data needs to be expanded. If the word count comparison result is that the initial word count is equal to the required word count of the paragraph, the initial paragraph data does not need to be modified. The initial paragraph data corresponding to the bid title is modified according to the word count comparison result. For example, if the initial word count is less than the required word count of the paragraph, adjectives or sentences related to keywords can be added according to the missing words. If the initial word count is greater than the required word count of the paragraph, sentences with less relevance to the keyword content or adjectives can be deleted according to the extra words to obtain the bid paragraph data corresponding to the bid title.

[0085] By obtaining the initial word count of the initial paragraph data corresponding to the bid title; comparing the initial word count with the required word count of the paragraph to obtain the word count comparison result; modifying the initial paragraph data corresponding to the bid title according to the word count comparison result to obtain the bid paragraph data corresponding to the bid title, different operations can be performed according to different word count comparison results, thereby improving the accuracy of bid generation.

[0086] Optionally, obtaining the bid body data includes: obtaining at least one historical bid text and at least one technical solution text, the historical bid text includes: at least one historical title and historical paragraph text corresponding to each historical title, the technical solution text includes: at least one technical title and a technical solution corresponding to each technical title; obtaining at least one preset title; according to each preset title, obtaining a network query text corresponding to each preset title through a network query; fusing each historical title and the historical paragraph text corresponding to each historical title, each technical title and the technical solution corresponding to each technical title, and each preset title and the network query text corresponding to the preset title to obtain the bid body data.

[0087] The historical bid text may be the text of the bid in the historical time period. The historical title may be the title of the chapter of the bid in the historical time period. The historical paragraph text may be the content of the bid corresponding to the historical title. The technical solution text may be the text describing the technical solution. The technical title may be the technical terms in the technical solution text. The technical solution may be the description information of the technical solution corresponding to the technical text. The preset title may be the preset bid title. The network query text may be the text related to the preset title obtained from the network.

[0088] Specifically, a historical time period is obtained, and at least one historical bid document text and at least one technical solution text are obtained according to the historical time period. At the same time, at least one preset title can be obtained, and according to each preset title, a network query text corresponding to each preset title is obtained through network query, and the latest updated text data on the network can be obtained, and each historical title and the historical paragraph text corresponding to each historical title, each technical title and the technical solution corresponding to each technical title, and each preset title and the network query text corresponding to the preset title are merged to obtain the bid document text data.

[0089] By obtaining at least one historical bid text and at least one technical solution text, the historical bid text includes: at least one historical title and the historical paragraph text corresponding to each historical title, and the technical solution text includes: at least one technical title and the technical solution corresponding to each technical title; obtaining at least one preset title; according to each preset title, obtaining the network query text corresponding to each preset title through network query; fusing each historical title and the historical paragraph text corresponding to each historical title, each technical title and the technical solution corresponding to each technical title, and each preset title and the network query text corresponding to the preset title to obtain the bid text data, the bid text data can be expanded in three aspects, so that the bid content is more accurate, and the content that is more in line with the development of modern science and technology is generated, thereby improving the accuracy of bid generation.

[0090] Optionally, obtaining the bid background data includes: obtaining at least one background parameter to be introduced; querying the company database according to each background parameter to be introduced to obtain the background introduction content corresponding to each introduction background parameter; and determining each introduction background parameter and the background introduction content corresponding to each introduction background parameter as the bid background data.

[0091] The background parameters to be introduced may be parameters of the content of the enterprise to be introduced, and the background introduction content may be introduction content corresponding to the background parameters to be introduced.

[0092] Specifically, at least one background parameter to be introduced is obtained. The parameter to be introduced may be the enterprise development history, enterprise vision and mission, number of successful enterprise bids, successful enterprise bid cases, technical methods of the enterprise's core competitiveness and the enterprise's core advantages, etc.

[0093] By obtaining at least one background parameter to be introduced; querying the company database according to each background parameter to be introduced to obtain the background introduction content corresponding to each introduction background parameter; determining each introduction background parameter and the background introduction content corresponding to each introduction background parameter as the bid background data, data with fixed content can be obtained without regeneration, and the corresponding data can be directly reused, thereby improving the efficiency of bid generation.

[0094] Embodiment 3

[0095] Figure 3The schematic diagram of the structure of a tender document generation device provided in the third embodiment of the present invention is shown in FIG. The embodiment of the present invention is applicable to the case of tender document generation, the device can execute the tender document generation method, and the device can be implemented in the form of hardware and / or software.

[0096] See also Figure 3 The bidding document generating device shown in the figure comprises: a bidding document data acquiring module 301, a screening text acquiring module 302, a text recognition module 303, a paragraph data acquiring module 304 and a bidding document generating module 305, wherein:

[0097] The tender document data acquisition module 301 is used to acquire the tender document text data and tender document background data;

[0098] The screening text acquisition module 302 is used to acquire the screening text, where the screening text includes: at least one screening parameter and the screening conditions corresponding to each screening parameter;

[0099] A text recognition module 303 is used to recognize the screening text to obtain at least one tender title and at least one tender keyword corresponding to each tender title;

[0100] The paragraph data acquisition module 304 is used to query the bid document body data for each bid document title according to each bid document keyword corresponding to the bid document title to obtain the bid document paragraph data corresponding to the bid document title;

[0101] The bid document generation module 305 is used to generate a target bid document according to each bid document title, bid document paragraph data corresponding to each bid document title, and bid document background data.

[0102] The technical solution of the embodiment of the present invention obtains the bid body data and bid background data; obtains the screening text, the screening text includes: at least one screening parameter and the screening conditions corresponding to each screening parameter; identifies the screening text to obtain at least one bid title and at least one bid keyword corresponding to each bid title; for each bid title, according to each bid keyword corresponding to the bid title, queries in the bid body data to obtain the bid paragraph data corresponding to the bid title; generates a target bid according to each bid title, the bid paragraph data corresponding to each bid title and the bid background data, and generates the bid through multi-dimensional data, thereby improving the accuracy of bid generation, and eliminating the need for manual bid writing, thereby improving the efficiency of bid generation.

[0103] Optionally, the paragraph data acquisition module 304 includes:

[0104] A demand data acquisition unit, used to acquire the required word count of the paragraph corresponding to the bid title and the keyword similarity requirement range;

[0105] A similar word determination unit, for determining, for each bid document keyword corresponding to the bid document title, at least one similar keyword corresponding to the bid document keyword according to a keyword similarity requirement range corresponding to the bid document title;

[0106] An initial data acquisition unit, used to query the tender body data to obtain initial paragraph data corresponding to the tender title according to the similar keywords corresponding to the tender title;

[0107] The paragraph data screening unit is used to screen the initial paragraph data corresponding to the bid title according to the required number of words of the paragraph corresponding to the bid title, so as to obtain the bid paragraph data corresponding to the bid title.

[0108] Optionally, the similar character determining unit is specifically used to:

[0109] Acquire at least one keyword set, the keyword set including: bid keywords, candidate keywords, and similarity values ​​between the bid keywords and the candidate keywords;

[0110] Determine at least one target set in each keyword set according to the similarity values ​​between the bid keywords in each keyword set and the keywords to be selected and the keyword similarity requirement range;

[0111] At least one similar keyword corresponding to the bid keyword is determined according to the candidate keywords in each target set.

[0112] Optionally, the initial data acquisition unit is specifically used to:

[0113] Obtaining a word weight set, the word weight set comprising: at least one bid word and an expected weight corresponding to each bid word;

[0114] According to the similar keywords corresponding to the bid title, the expected weight corresponding to each similar keyword is obtained by querying in the text weight set;

[0115] Determine the content query order according to the expected weights corresponding to each similar keyword;

[0116] The initial paragraph data corresponding to the bid title is obtained by searching in the bid body data according to the content search order.

[0117] Optional, paragraph data filtering unit, specifically used for:

[0118] Get the initial word count of the initial paragraph data corresponding to the bid title;

[0119] Compare the initial word count with the required word count of the paragraph to obtain a word count comparison result;

[0120] The initial paragraph data corresponding to the bid title is modified according to the word count comparison result to obtain the bid paragraph data corresponding to the bid title.

[0121] Optionally, the bid data acquisition module 301 is specifically used for:

[0122] Acquire at least one historical tender document text and at least one technical solution text, wherein the historical tender document text includes: at least one historical title and a historical paragraph text corresponding to each historical title, and the technical solution text includes: at least one technical title and a technical solution corresponding to each technical title;

[0123] Get at least one preset title;

[0124] According to each preset title, obtain the network query text corresponding to each preset title through network query;

[0125] Each historical title and the historical paragraph text corresponding to each historical title, each technical title and the technical solution corresponding to each technical title, and each preset title and the network query text corresponding to the preset title are integrated to obtain the bid text data.

[0126] Optionally, the bid data acquisition module 301 is specifically used for:

[0127] Obtain at least one background parameter to be introduced;

[0128] According to each background parameter to be introduced, the background introduction content corresponding to each introduction background parameter is obtained by searching in the company database;

[0129] Each introduction background parameter and the background introduction content corresponding to each introduction background parameter are determined as the bid document background data.

[0130] The bid generation device provided in the embodiment of the present invention can execute the bid generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the bid generation method.

[0131] Embodiment 4

[0132] Figure 4 A schematic diagram of the structure of a bid generating device 400 that can be used to implement an embodiment of the present invention is shown.

[0133] like Figure 4As shown, the bid generation device 400 includes at least one processor 401, and a memory connected to the at least one processor 401, such as a read-only memory (ROM) 402, a random access memory (RAM) 403, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 401 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 402 or the computer program loaded from the storage unit 408 to the random access memory (RAM) 403. Various programs and data required for the operation of the bid generation device 400 can also be stored in the RAM 403. The processor 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0134] A number of components in the bid generation device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the bid generation device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0135] Processor 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. Processor 501 executes the various methods and processes described above, such as a bid generation method.

[0136] In some embodiments, the bid generation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the bid generation device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the processor 401, one or more steps of the bid generation method described above may be performed. Alternatively, in other embodiments, the processor 401 may be configured to execute the bid generation method in any other appropriate manner (e.g., by means of firmware).

[0137] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0139] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] To provide interaction with a user, the systems and techniques described herein may be implemented on a bid generation device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the bid generation device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0141] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0142] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0143] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0144] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a tender document, characterized in that: The method comprises: Obtain the tender document body data and tender document background data; Acquire a screening text, wherein the screening text includes: at least one screening parameter and a screening condition corresponding to each of the screening parameters; Identify the screening text to obtain at least one tender title and at least one tender keyword corresponding to each tender title; For each of the bid titles, according to each of the bid keywords corresponding to the bid title, query the bid text data to obtain the bid paragraph data corresponding to the bid title; A target bid is generated according to each of the bid titles, the bid paragraph data corresponding to each of the bid titles and the bid background data.

2. The method according to claim 1, characterized in that The step of searching the bid text data for bid paragraph data corresponding to the bid title according to the bid keywords corresponding to the bid title includes: Obtain the required word count and keyword similarity requirement range of the paragraph corresponding to the bid title; For each of the bid document keywords corresponding to the bid document title, determining at least one similar keyword corresponding to the bid document keyword according to the keyword similarity requirement range corresponding to the bid document title; According to each of the similar keywords corresponding to the bid title, query the bid body data to obtain the initial paragraph data corresponding to the bid title; The initial paragraph data corresponding to the bid document title is screened according to the required number of words of the paragraph corresponding to the bid document title to obtain the bid document paragraph data corresponding to the bid document title.

3. The method according to claim 2, characterized in that The determining at least one similar keyword corresponding to the bid document keyword according to the keyword similarity requirement range corresponding to the bid document title includes: Acquire at least one keyword set, the keyword set including: the bid keyword, the candidate keyword, and a similarity value between the bid keyword and the candidate keyword; Determine at least one target set in each of the keyword sets according to the similarity values ​​between the bid keywords in each of the keyword sets and the candidate keywords and the keyword similarity requirement range; At least one similar keyword corresponding to the bid keyword is determined according to the candidate keywords in each of the target sets.

4. The method according to claim 2, characterized in that: The step of searching the text data of the tender document to obtain the initial paragraph data corresponding to the tender document title according to the similar keywords corresponding to the tender document title includes: Acquire a word weight set, the word weight set comprising: at least one bid word and an expected weight corresponding to each bid word; According to each of the similar keywords corresponding to the bid title, query in the text weight set to obtain the expected weight corresponding to each of the similar keywords; Determining a content query order according to the expected weights corresponding to the similar keywords; The initial paragraph data corresponding to the bid title is obtained by searching the bid body data according to the content search sequence.

5. The method according to claim 2, characterized in that: The initial paragraph data corresponding to the bid document title is screened according to the required number of words of the paragraph corresponding to the bid document title to obtain the bid document paragraph data corresponding to the bid document title, including: Obtaining the initial word count of the initial paragraph data corresponding to the bid title; Compare the initial word count with the required word count of the paragraph to obtain a word count comparison result; The initial paragraph data corresponding to the bid title is modified according to the word count comparison result to obtain the bid paragraph data corresponding to the bid title.

6. The method according to claim 1, characterized in that The obtaining of the bid document body data includes: Acquire at least one historical bid document text and at least one technical solution text, wherein the historical bid document text includes: at least one historical title and a historical paragraph text corresponding to each of the historical titles, and the technical solution text includes: at least one technical title and a technical solution corresponding to each of the technical titles; Get at least one preset title; According to each of the preset titles, obtaining a network query text corresponding to each of the preset titles through network query; Each of the historical titles and the historical paragraph text corresponding to each of the historical titles, each of the technical titles and the technical solutions corresponding to each of the technical titles, and each of the preset titles and the network query text corresponding to the preset titles are merged to obtain the bid text data.

7. The method according to claim 1, characterized in that The obtaining of bid document background data includes: Obtain at least one background parameter to be introduced; According to each of the background parameters to be introduced, query the company database to obtain the background introduction content corresponding to each of the introduction background parameters; The introduction background parameters and the background introduction contents corresponding to the introduction background parameters are determined as the tender background data.

8. A tender document generating device, characterized in that: The device comprises: The tender document data acquisition module is used to acquire the tender document body data and tender document background data; A screening text acquisition module, used to acquire screening text, wherein the screening text includes: at least one screening parameter and screening conditions corresponding to each of the screening parameters; A text recognition module, used for recognizing the screening text to obtain at least one tender title and at least one tender keyword corresponding to each tender title; A paragraph data acquisition module, for querying the bid document paragraph data corresponding to each bid document title in the bid document body data according to each bid document keyword corresponding to the bid document title; The bid document generation module is used to generate a target bid document according to each bid document title, bid document paragraph data corresponding to each bid document title and the bid document background data.

9. A tender document generating device, characterized in that: The bid generation device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the bid generation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the bid generation method according to any one of claims 1 to 7 when executed.

Images