Bidding and tendering auxiliary decision-making method and system based on artificial intelligence

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a bidding and tendering auxiliary decision-making method and system based on artificial intelligence, and the method comprises the steps: determining an access period corresponding to channel address information in a target bidding information demand aspect according to the bidding information updating frequency of a bidding information channel, according to the access period and the channel address information, initiating an access operation aiming at the bid invitation information channel so as to access all current bid invitation information published by the bid invitation information channel; screening out a plurality of pieces of to-be-determined bid invitation information from all the current bid invitation information, and for each piece of to-be-determined bid invitation information, calculating a capability matching degree corresponding to the demand aspect of the target bid invitation information to each piece of to-be-determined bid invitation information according to the corresponding multi-dimensional demand information of the to-be-determined bid invitation information and the multi-dimensional capability attribute information corresponding to the target bid invitation information demand side; and screening out the target bid invitation information from all the to-be-determined bid invitation information and pushing the target bid invitation information to a target bid invitation information demander according to the capability matching degree of the target bid invitation information demand aspect to each piece of to-be-determined bid invitation information. Therefore, intelligent screening of the bid invitation information can be realized, and the screening efficiency and the screening reliability of the bid invitation information can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based bidding and tendering decision-making auxiliary method and system. Background Art

[0002] At present, many projects (such as construction projects, software development projects, etc.) need to find suitable implementers through the bidding process before actual implementation, that is: the demander publishes bidding requirements according to project requirements, and the bidder compiles and provides bidding documents according to the bidding requirements. The bidding documents are reviewed by the demander's internal reviewers or by third-party reviewers, and then the target bidder that meets the requirements is selected, and then a project implementation relationship is established between the demander and the target bidder, and then the target bidder acts as the implementer to implement or jointly implement the demander's project.

[0003] For the bidder, it is necessary for relevant personnel to pay attention to the bidding website regularly or irregularly, and then gradually screen from a number of bidding information, and finally screen out the bidding information that matches itself and then bid. That is, the bidder needs to manually screen the bidding information that matches it. This method of screening bidding information has the problems of low screening efficiency and low screening reliability.

[0004] It can be seen that how to realize intelligent screening of bidding information to improve the screening efficiency and reliability of bidding information is particularly important. Summary of the invention

[0005] The present invention provides a bidding and tendering decision-making auxiliary method and system based on artificial intelligence, which can realize intelligent screening of bidding information and is conducive to improving the screening efficiency and screening reliability of bidding information.

[0006] The first aspect of the present invention discloses a bidding decision-making assistance method based on artificial intelligence, the method comprising:

[0007] Determine the channel address information corresponding to the bidding information channel that matches the target bidding information demander;

[0008] Based on the historical update information corresponding to the channel address information and the category of the tender information publisher settled in the tender information channel, analyzing the tender information update frequency corresponding to the channel address information;

[0009] Determine the access cycle corresponding to the channel address information of the target tender information demand according to the tender information update frequency, and initiate an access operation for the tender information channel according to the access cycle and the channel address information, wherein the access operation is used to access all current tender information published by the tender information channel;

[0010] Filtering out a plurality of pending tender information from all the current tender information, and for each of the pending tender information, calculating the degree of matching of the target tender information demand with the capability corresponding to each of the pending tender information according to the corresponding multi-dimensional demand information and the multi-dimensional capability attribute information corresponding to the target tender information demander;

[0011] According to the capability matching degree of the target bidding information demand to each of the pending bidding information, the target bidding information is screened out from all the pending bidding information, and the target bidding information is pushed to the target bidding information demander; wherein the capability matching degree of the target bidding information demand to the target bidding information satisfies a preset matching degree condition.

[0012] As an optional implementation manner, in the first aspect of the present invention, after pushing the target bidding information to the target bidding information demander, the method further includes:

[0013] Based on the multi-dimensional demand information corresponding to the target bidding information and the multi-dimensional capability attribute information corresponding to the target bidding information demander, the multi-dimensional matching degree between the target bidding information and the target bidding information demander is calculated. If there is a target matching degree that does not meet the matching degree condition in the multi-dimensional matching degree, then based on the target dimension corresponding to the target matching degree, the target demand information that matches the target dimension in the multi-dimensional demand information corresponding to the target bidding information, and the target capability attribute information that matches the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, the influencing factors of the target matching degree not meeting the matching degree condition are analyzed, and based on the influencing factors, a capability attribute optimization strategy corresponding to the target bidding information demander is generated, and the capability attribute optimization strategy is pushed to the target bidding information demander.

[0014] As an optional implementation manner, in the first aspect of the present invention, if there is a target matching degree that does not satisfy the matching degree condition in the multidimensional matching degree, then based on the target dimension corresponding to the target matching degree, the target demand information that matches the target dimension in the multidimensional demand information corresponding to the target bidding information, and the target capability attribute information that matches the target dimension in the multidimensional capability attribute information corresponding to the target bidding information demander, before analyzing the influencing factors that the target matching degree does not satisfy the matching degree condition, the method further includes:

[0015] If the target tender information is pushed to multiple tender information demanders, the degree of demand for the target tender information by the target tender information demander compared with other tender information demanders is analyzed. If the degree of demand is greater than or equal to the preset degree threshold, the bidding competitiveness of the target tender information demander for the target tender information is analyzed compared with the other tender information demanders. If the bidding competitiveness is greater than or equal to the preset competitiveness threshold, the step of analyzing the influencing factors of the target matching degree not satisfying the matching degree condition based on the target dimension corresponding to the target matching degree, the target demand information matching the target dimension in the multi-dimensional demand information corresponding to the target tender information, and the target capability attribute information matching the target dimension in the multi-dimensional capability attribute information corresponding to the target tender information demander is triggered.

[0016] As an optional implementation manner, in the first aspect of the present invention, generating a capability attribute optimization strategy corresponding to the target tender information demander based on the influencing factors includes:

[0017] According to the target capability attribute that matches the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, estimate the difficulty coefficient of adjusting the target capability attribute to weaken or eliminate the influencing factor;

[0018] According to the difficulty coefficient, determining the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander, and analyzing the adjustment direction corresponding to the capability attribute to be adjusted;

[0019] According to the adjustment direction corresponding to the capability attribute to be adjusted, a capability attribute optimization strategy corresponding to the capability attribute to be adjusted is generated as the capability attribute optimization strategy corresponding to the target bidding information demander.

[0020] As an optional implementation manner, in the first aspect of the present invention, determining, according to the difficulty coefficient, the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander includes:

[0021] If the difficulty coefficient is less than or equal to the preset difficulty coefficient threshold, the target capability attribute is determined as the capability attribute to be adjusted; if the difficulty coefficient is greater than the preset difficulty coefficient threshold, the capability attribute to be adjusted is determined from the remaining capability attributes except the target capability attribute;

[0022] The step of determining the capability attribute to be adjusted from the remaining capability attributes except the target capability attribute includes:

[0023] Determining a plurality of optional capability attributes having adjustment space from the remaining capability attributes except the target capability attribute;

[0024] For each of the optional capability attributes, analyzing the difficulty of adjusting the optional capability attribute and the degree to which adjusting the optional capability attribute improves the bidding competitiveness of the target bidding information in terms of the demand of the target bidding information, and obtaining a selection reference basis corresponding to the optional capability attribute;

[0025] According to the selection references corresponding to all the optional capability attributes, the capability attributes to be adjusted are determined from all the optional capability attributes.

[0026] As an optional implementation manner, in the first aspect of the present invention, the estimating and adjusting the target capability attribute to weaken or eliminate the difficulty coefficient of the influencing factor includes:

[0027] Determining the target capability attribute to weaken or eliminate the first difficulty coefficient of the influencing factor according to the internal resources of the target tender information demander;

[0028] Determining the target capability attribute to weaken or eliminate the second difficulty coefficient of the influencing factor according to the internal resources of the target bidding information demander;

[0029] Determining a comprehensive difficulty coefficient according to the first difficulty coefficient and the second difficulty coefficient;

[0030] Based on the current time and the deadline for receiving the bidding documents of the target bidding information, the time difficulty calibration coefficient is determined, and the comprehensive difficulty coefficient is calibrated based on the difficulty calibration coefficient to obtain the difficulty coefficient for adjusting the target ability attribute to weaken or eliminate the influencing factors.

[0031] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0032] Collecting the operation behavior of the target tender information demander after receiving the target tender information, predicting the probability of the target tender information demander bidding on the target tender information based on the operation behavior, and if the probability is greater than or equal to a preset probability threshold, analyzing the target tender information, and extracting the tender document format requirements and multiple key information required for the tender from the target tender information;

[0033] For all the key information, all the key information is divided into first-category key information and second-category key information according to the acquisition method of the key information, wherein the first-category key information includes key information that can be queried or extracted through public channels;

[0034] Arranging the initial bidding document according to the bidding document format requirements and the first type of key information obtained based on the way of obtaining the first type of key information, and providing the initial bidding document to the target bidding information demander;

[0035] And, the method further comprises:

[0036] For the second category of key information, the recommended time range for organizing the second category of key information is determined based on the acquisition method, organization complexity and deadline for organizing the tender documents of the second category of key information, and the recommended time range for organizing the second category of key information is provided to the target tender information demander.

[0037] The second aspect of the present invention discloses an artificial intelligence-based bidding decision-making auxiliary system, the system comprising:

[0038] A channel determination module is used to determine the channel address information corresponding to the bidding information channel that matches the target bidding information demander;

[0039] An information access module is used to analyze the tender information update frequency corresponding to the channel address information based on the historical update information corresponding to the channel address information and the category of tender information publishers settled in the tender information channel; determine the access cycle corresponding to the channel address information of the target tender information demand according to the tender information update frequency, and initiate an access operation for the tender information channel according to the access cycle and the channel address information, wherein the access operation is used to access all current tender information published by the tender information channel;

[0040] An information recommendation module is used to filter out multiple pending tender information from all the current tender information, and for each pending tender information, calculate the capability matching degree of the target tender information demand to each pending tender information according to its corresponding multi-dimensional demand information and the multi-dimensional capability attribute information corresponding to the target tender information demander, and, according to the capability matching degree of the target tender information demand to each pending tender information, filter out the target tender information from all the pending tender information, and push the target tender information to the target tender information demander; wherein, the capability matching degree of the target tender information demand to the target tender information meets a preset matching condition.

[0041] As an optional implementation, in the second aspect of the present invention, the system further includes:

[0042] An optimization suggestion module is used to calculate the multi-dimensional matching degree between the target bidding information and the target bidding information demander based on the multi-dimensional demand information corresponding to the target bidding information and the multi-dimensional capability attribute information corresponding to the target bidding information demander. If there is a target matching degree that does not meet the matching degree condition in the multi-dimensional matching degree, then based on the target dimension corresponding to the target matching degree, the target demand information matching the target dimension in the multi-dimensional demand information corresponding to the target bidding information, and the target capability attribute information matching the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, analyze the influencing factors of the target matching degree not meeting the matching degree condition, and based on the influencing factors, generate a capability attribute optimization strategy corresponding to the target bidding information demander, and push the capability attribute optimization strategy to the target bidding information demander.

[0043] As an optional implementation, in the second aspect of the present invention, the optimization suggestion module is further used to:

[0044] If the target tender information is pushed to multiple tender information demanders, the degree of demand for the target tender information by the target tender information demander compared with other tender information demanders is analyzed. If the degree of demand is greater than or equal to the preset degree threshold, the bidding competitiveness of the target tender information demander for the target tender information compared with other tender information demanders is analyzed. If the bidding competitiveness is greater than or equal to the preset competitiveness threshold, the operation of analyzing the influencing factors of the target matching degree not satisfying the matching degree condition based on the target dimension corresponding to the target matching degree, the target demand information matching the target dimension in the multi-dimensional demand information corresponding to the target tender information, and the target capability attribute information matching the target dimension in the multi-dimensional capability attribute information corresponding to the target tender information demander is triggered.

[0045] As an optional implementation, in the second aspect of the present invention, the specific manner in which the optimization suggestion module generates the capability attribute optimization strategy corresponding to the target tender information demander based on the influencing factors includes:

[0046] According to the target capability attribute that matches the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, estimate the difficulty coefficient of adjusting the target capability attribute to weaken or eliminate the influencing factor;

[0047] According to the difficulty coefficient, determining the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander, and analyzing the adjustment direction corresponding to the capability attribute to be adjusted;

[0048] According to the adjustment direction corresponding to the capability attribute to be adjusted, a capability attribute optimization strategy corresponding to the capability attribute to be adjusted is generated as the capability attribute optimization strategy corresponding to the target bidding information demander.

[0049] As an optional implementation, in the second aspect of the present invention, the optimization suggestion module determines, according to the difficulty coefficient, a specific manner in which the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander comprises:

[0050] If the difficulty coefficient is less than or equal to the preset difficulty coefficient threshold, the target capability attribute is determined as the capability attribute to be adjusted; if the difficulty coefficient is greater than the preset difficulty coefficient threshold, the capability attribute to be adjusted is determined from the remaining capability attributes except the target capability attribute;

[0051] The specific manner in which the optimization suggestion module determines the capability attribute to be adjusted from the remaining capability attributes except the target capability attribute includes:

[0052] Determining a plurality of optional capability attributes having adjustment space from the remaining capability attributes except the target capability attribute;

[0053] For each of the optional capability attributes, analyzing the difficulty of adjusting the optional capability attribute and the degree to which adjusting the optional capability attribute improves the bidding competitiveness of the target bidding information in terms of the demand of the target bidding information, and obtaining a selection reference basis corresponding to the optional capability attribute;

[0054] According to the selection references corresponding to all the optional capability attributes, the capability attributes to be adjusted are determined from all the optional capability attributes.

[0055] As an optional implementation, in the second aspect of the present invention, the specific manner in which the optimization suggestion module estimates the difficulty coefficient of adjusting the target capability attribute to weaken or eliminate the influencing factor includes:

[0056] Determining the target capability attribute to weaken or eliminate the first difficulty coefficient of the influencing factor according to the internal resources of the target tender information demander;

[0057] Determining the target capability attribute to weaken or eliminate the second difficulty coefficient of the influencing factor according to the internal resources of the target bidding information demander;

[0058] Determining a comprehensive difficulty coefficient according to the first difficulty coefficient and the second difficulty coefficient;

[0059] Based on the current time and the deadline for receiving the bidding documents of the target bidding information, the time difficulty calibration coefficient is determined, and the comprehensive difficulty coefficient is calibrated based on the difficulty calibration coefficient to obtain the difficulty coefficient for adjusting the target ability attribute to weaken or eliminate the influencing factors.

[0060] As an optional implementation, in the second aspect of the present invention, the system further includes a bidding assistance module, wherein:

[0061] The bidding auxiliary module is used to collect the operation behavior of the target bidding information demander after receiving the target bidding information, and predict the probability of the target bidding information demander bidding the target bidding information based on the operation behavior; if the probability is greater than or equal to a preset probability threshold, the target bidding information is analyzed, and the bidding document format requirements and multiple key information required for bidding are extracted from the target bidding information; for all the key information, all the key information are divided into a first category of key information and a second category of key information according to the acquisition method of the key information, and the first category of key information includes key information that can be queried or extracted through public channels; according to the bidding document format requirements and the first category of key information obtained based on the acquisition method of the first category of key information, the initial bidding document is sorted out, and the initial bidding document is provided to the target bidding information demander;

[0062] In addition, the bidding assistance module is also used to determine the recommended time range for organizing the second category of key information based on the acquisition method, organization complexity and bidding document organization deadline of the second category of key information, and provide the recommended time range for organizing the second category of key information to the target bidding information demander.

[0063] The third aspect of the present invention discloses another bidding and tendering decision-making auxiliary system based on artificial intelligence, the system comprising:

[0064] A memory storing executable program code;

[0065] a processor coupled to the memory;

[0066] The processor calls the executable program code stored in the memory to execute part or all of the steps in the artificial intelligence-based bidding and tendering decision-making assistance method disclosed in the first aspect of the present invention.

[0067] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the artificial intelligence-based bidding and tendering decision-making support method disclosed in the first aspect of the present invention.

[0068] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0069] In the embodiment of the present invention, after determining the address information corresponding to the bidding information channel, the update frequency of the bidding information can be analyzed according to the multi-dimensional information to determine the appropriate access cycle, which is conducive to improving the timeliness of access to the bidding information. After the bidding information channel accesses multiple bidding information, the pending bidding information is first preliminarily screened out, and then the ability matching degree corresponding to each pending bidding information in terms of bidding information demand is calculated, and then the bidding information demander is screened and recommended based on the ability matching degree for the bidding information demander, and the bidding information whose ability matching degree meets the preset matching degree condition is realized, which is conducive to improving the screening efficiency and screening reliability of the bidding information. In addition, after recommending the appropriate target bidding information to the bidding information demander, the multi-dimensional matching degree between the two (that is, the matching degree between multiple dimensions) can also be calculated. If there is a target matching degree that does not meet the matching degree condition, the corresponding influencing factors are further intelligently analyzed, and the ability attribute optimization strategy is generated based on the analyzed influencing factors, which is conducive to improving the generation accuracy of the ability attribute optimization strategy, and then it is conducive to further improving the competitiveness of the bidding information demander to the target bidding information, that is: it is conducive to further improving the matching degree between the bidding information demander and the target bidding information. In addition, before analyzing the influencing factors that cause the target matching degree to fail to meet the matching degree conditions, it is also possible to further combine the number of tender information demanders to which the target tender information is pushed, the degree of demand for the target tender information by the target tender information demanders, and the bidding competitiveness of the target tender information demanders compared to other tender information demanders to comprehensively judge whether it is necessary to analyze the influencing factors, which is conducive to improving the reliability of the analysis of the influencing factors, and thus to improving the reliability of the generation of the capability attribute optimization strategy. In addition, when generating the capability attribute optimization strategy, it is also possible to determine the capability attribute to be adjusted based on the estimated capability attribute adjustment difficulty coefficient, and further generate the capability attribute optimization strategy based on the adjustment direction corresponding to the capability attribute to be adjusted, which is conducive to improving the reliability of the generation of the capability attribute optimization strategy.In addition, the ability attributes to be adjusted can be intelligently determined according to the size of the ability attribute adjustment difficulty coefficient and the preset difficulty coefficient threshold, which is conducive to improving the reliability of determining the ability attributes to be adjusted. Furthermore, when determining the ability attributes to be adjusted from the remaining ability attributes, it is possible to obtain the selection reference corresponding to the remaining ability attributes based on the adjustment difficulty corresponding to the remaining ability attributes and the degree of improvement in the bidding competitiveness of the target bidding information after the adjustment, which is conducive to improving the reliability of determining the ability attributes to be adjusted from the remaining ability attributes, that is: improving the matching degree between the determined ability attributes to be adjusted and the improvement demand for the bidding competitiveness of the target bidding information demander; in addition, when estimating the difficulty of adjusting the target ability attributes When calculating the coefficient, the comprehensive difficulty coefficient can be determined based on internal and external resources, and then the comprehensive difficulty coefficient can be calibrated based on the time difficulty calibration coefficient, which is conducive to improving the estimated accuracy of the difficulty coefficient of adjusting the target capability attribute; in addition, it is also possible to predict the bidding probability of the target bidding information demander based on its operation behavior after recommending the target bidding information to the target bidding information demander. If the bidding probability is large, the initial bidding document can be generated according to the key information acquisition method and the bidding document format requirements, which is conducive to assisting the generation of bidding documents and improving the convenience of generating bidding documents. It can also generate a recommended sorting time range for the second type of key information, reducing the situation where the complete bidding document cannot be sorted out due to insufficient time and the bidding time is missed. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. 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.

[0071] Figure 1 It is a flowchart of an artificial intelligence-based bidding decision-making assistance method disclosed in an embodiment of the present invention;

[0072] Figure 2 It is a structural schematic diagram of an artificial intelligence-based bidding and tendering decision-making assistance system disclosed in an embodiment of the present invention;

[0073] Figure 3 It is a structural schematic diagram of another bidding and tendering decision-making auxiliary system based on artificial intelligence disclosed in an embodiment of the present invention;

[0074] Figure 4 It is a structural diagram of another bidding and tendering decision-making support system based on artificial intelligence disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0075] 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 are within the scope of protection of the present invention.

[0076] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0077] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0078] The present invention discloses a bidding and tendering decision-making assistance method and system based on artificial intelligence. After determining the address information corresponding to the bidding information channel, the bidding information update frequency can be analyzed according to multi-dimensional information to determine the appropriate access cycle, which is conducive to improving the timeliness of access to the bidding information. After accessing multiple bidding information through the bidding information channel, the pending bidding information is preliminarily screened out, and then the ability matching degree corresponding to each pending bidding information in terms of bidding information demand is calculated, and then based on the ability matching degree, the bidding information demander is screened and recommended for the bidding information whose ability matching degree meets the preset matching degree condition, realizing the intelligent screening of the bidding information, which is conducive to improving the screening efficiency and screening reliability of the bidding information. The following are detailed descriptions.

[0079] Embodiment 1

[0080] See also Figure 1 , Figure 1 This is a flowchart of an artificial intelligence-based bidding decision-making assistance method disclosed in an embodiment of the present invention. Figure 1The described method is applied to a bidding and tendering decision-making support system, which can be integrated with a local server or a cloud server, and the embodiments of the present invention do not limit this. Figure 1 As shown, the method may include the following operations:

[0081] 101. Determine the channel address information corresponding to the bidding information channel that matches the target bidding information demander.

[0082] In the embodiment of the present invention, the target tender information demander is any enterprise that can provide services to the outside and has bidding needs, and the tender information channel matching the target tender information demander can be intelligently analyzed based on the services that the target tender information demander can provide to the outside, or it can be selected or configured by the target tender information demander itself, or it can be a combination of the two, which is not limited in the embodiment of the present invention.

[0083] 102. Based on the historical update information corresponding to the channel address information and the category of tender information publishers in the tender information channel, analyze the tender information update frequency corresponding to the channel address information.

[0084] In an embodiment of the present invention, analyzing the tender information update frequency corresponding to the channel address information can specifically be analyzing the tender information update frequency that matches the services that the target tender information demander can provide externally, or analyzing the tender information update frequency corresponding to the tender information category that the target tender information demander is concerned about.

[0085] 103. Determine the access cycle corresponding to the channel address information in terms of target tender information demand according to the tender information update frequency, and initiate an access operation for the tender information channel according to the access cycle and the channel address information. The access operation is used to access all current tender information released by the tender information channel.

[0086] In an embodiment of the present invention, all current bidding information released by the bidding information channel specifically includes bidding information released by the bidding information channel that has not exceeded the bid document receiving time range and the time length from the bid document receiving time range is greater than or equal to the preset time length threshold.

[0087] 104. Filter out multiple pending tender information from all current tender information. For each pending tender information, calculate the capability matching degree of the target tender information demand to each pending tender information according to its corresponding multi-dimensional demand information and the multi-dimensional capability attribute information corresponding to the target tender information demander.

[0088] In the embodiment of the present invention, the above-mentioned screening out a plurality of pending bidding information from all current bidding information includes:

[0089] Determine all historical bidding information accessed in the latest historical access cycle that matches the target bidding information demander, determine the intersection bidding information between the aforementioned historical bidding information and all the aforementioned current bidding information, and select multiple pending bidding information from the bidding information of all the aforementioned current bidding information except the aforementioned intersection bidding information.

[0090] Furthermore, selecting a plurality of pending tender information from all the current tender information except the aforementioned intersection tender information may include:

[0091] A plurality of pending tender information matching the current external service category of the target tender information demander is screened out from the tender information of all the current tender information except the aforementioned intersection tender information. Optionally, the current external service category of the target tender information demander can be comprehensively determined based on the target tender information demander's own service resources and / or the target tender information demander's external cooperation resources, or the current external service category of the target tender information demander can be pre-set by the enterprise's bidding and tendering personnel, such as setting one or a group of keywords corresponding to the service category, and the set keywords corresponding to the service category can be adjusted according to the situation of the target tender information demander.

[0092] In an embodiment of the present invention, the multi-dimensional demand information corresponding to the pending bidding information may specifically include multiple service resource demand types (such as personnel, equipment, etc.), the demand range corresponding to each service resource demand type, and the scoring values ​​of different ranges corresponding to each service resource demand type. The target bidding information demand aspect is calculated to match the capability corresponding to each pending bidding information, that is, according to the demand range corresponding to each service resource demand type and the scoring values ​​of different ranges corresponding to each service resource demand type, the multi-dimensional capability attribute information corresponding to the target bidding information demander is comprehensively scored.

[0093] 105. According to the capability matching degree of the target tender information demand to each pending tender information, the target tender information is screened out from all pending tender information, and the target tender information is pushed to the target tender information demander; wherein the capability matching degree of the target tender information demand to the target tender information satisfies the preset matching degree condition.

[0094] Among them, the ability matching degree of the target tender information demand to the target tender information meets the preset matching degree condition, that is, the scoring value of the target tender information demand to the target tender information is within the preset scoring value range. Further, after the target tender information is pushed to the target tender information demander, the list page can display the brief tender information according to the viewing operation of the target tender information demander, and the details page can display the detailed information, support the remark information, and associate the original text URL. In addition, the list filtering dimension (such as time, category, information source) can be set according to the requirements of the business department. According to the follow operation / unfollow operation triggered by the target tender information demander, the target tender information demander can set the follow relationship with the target tender information / target tender information publisher, so as to conveniently and quickly realize the tender information management and information editing status.

[0095] Furthermore, it can also comprehensively display the tracking status of bidding opportunities (such as statistics on the total number and proportion of attention information this week, this month and this year, the proportion of each channel of source information, the cumulative total number of attention information this week, this month and this year, and the cumulative total number of collected information), so as to facilitate the target bidding information demanders to screen relevant information.

[0096] Furthermore, the bidding and tendering decision-making support system adopts a B / S architecture and can be deployed through a private cloud (Tencent Cloud, Alibaba Cloud, etc.). Users access the system through the public network and log in to the system with their account and password. Among them, when implementing the bidding and tendering support decision-making, one of the more common implementation processes may include:

[0097] 1. User logs into the system: The user logs in through the system login page.

[0098] 2. Configure the bidding website URL: The user enters the URL of the website where the bidding information needs to be obtained.

[0099] 3. Set the keywords you want to focus on: Users configure the keywords they want to focus on in order to filter information.

[0100] 4. The system obtains website data regularly: The system obtains the configured website data regularly (for example, daily or hourly).

[0101] 5. Analyze web page content: The system analyzes the acquired web page content and extracts relevant information.

[0102] 6. Filter information: The system filters out qualified bidding information based on the keywords set by the user.

[0103] 7. Deduplication and data cleaning: The system deduplicates and cleanses the filtered information to ensure its accuracy and completeness.

[0104] 8. Recommended bidding information: The system will recommend the screened bidding information to users.

[0105] 9. Users view recommended information: Users view recommended bidding information through the system interface.

[0106] 10. Mark information of interest: Users can mark the bidding information of interest so as to further follow up and pay attention to the information.

[0107] 11. Edit information classification: Users can set business classification for target bidding information in order to further follow up on statistical business scope.

[0108] 12. Generate reports for user reference: The system performs data statistics and analysis based on user operations and feedback, and updates the workbench for user decision-making reference.

[0109] It can be seen that the embodiment of the present invention can analyze the update frequency of the tender information according to the multi-dimensional information after determining the address information corresponding to the tender information channel, and then determine the appropriate access cycle, which is beneficial to improving the timeliness of access to the tender information. After accessing multiple tender information through the tender information channel, it first preliminarily screens out the pending tender information, and then calculates the capability matching degree corresponding to each pending tender information in terms of tender information demand, and then based on the capability matching degree, screens and recommends the tender information demander with the capability matching degree meeting the preset matching degree condition, thereby realizing the intelligent screening of tender information, which is beneficial to improving the screening efficiency and screening reliability of tender information.

[0110] Furthermore, after the target tender information is pushed to the target tender information demander, the target tender information demander can follow up and manage the selected tender information, allowing the target tender information demander to follow up, mark the status, add notes, etc. for the tender information of interest. Furthermore, the bidding and tendering decision-making support system can also automatically send reminder notifications to the newly obtained qualified tender information, such as sending reminders through multiple methods such as email, SMS or in-application notification.

[0111] In an optional embodiment, after pushing the target bidding information to the target bidding information demander, the method further includes:

[0112] Based on the multi-dimensional demand information corresponding to the target bidding information and the multi-dimensional capability attribute information corresponding to the target bidding information demander, the multi-dimensional matching degree between the target bidding information and the target bidding information demander is calculated. If there is a target matching degree that does not meet the matching degree condition in the multi-dimensional matching degree, then based on the target dimension corresponding to the target matching degree, the target demand information that matches the target dimension in the multi-dimensional demand information corresponding to the target bidding information, and the target capability attribute information that matches the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, the influencing factors of the target matching degree not meeting the matching degree condition are analyzed, and based on the influencing factors, a capability attribute optimization strategy corresponding to the target bidding information demander is generated, and the capability attribute optimization strategy is pushed to the target bidding information demander.

[0113] For example, assume that the target matching degree that does not meet the matching degree conditions is the equipment dimension corresponding to the construction equipment, and the corresponding influencing factors may be that the equipment of the target bidding information demander is relatively old / the equipment function has not been upgraded, and / or the number of equipment is insufficient, and / or the types of equipment are insufficient.

[0114] It can be seen that after recommending suitable target bidding information to the bidding information demander, this optional embodiment can also calculate the multi-dimensional matching degree between the two (that is, the matching degree between multiple dimensions). If there is a target matching degree that does not meet the matching conditions, the corresponding influencing factors are further analyzed intelligently, and a capability attribute optimization strategy is generated based on the analyzed influencing factors, which is conducive to improving the generation accuracy of the capability attribute optimization strategy, and further conducive to further improving the competitiveness of the bidding information demander to the target bidding information, that is: it is conducive to further improving the matching degree between the bidding information demander and the target bidding information.

[0115] In another optional embodiment, if there is a target matching degree that does not meet the matching degree condition in the multidimensional matching degree, then before analyzing the influencing factors that the target matching degree does not meet the matching degree condition based on the target dimension corresponding to the target matching degree, the target demand information that matches the target dimension in the multidimensional demand information corresponding to the target bidding information, and the target capability attribute information that matches the target dimension in the multidimensional capability attribute information corresponding to the target bidding information demander, the method further includes:

[0116] If the target tender information is pushed to multiple tender information demanders, the degree of demand for the target tender information by the target tender information demander compared with other tender information demanders is analyzed. If the degree of demand is greater than or equal to the preset degree threshold, the bidding competitiveness of the target tender information demander for the target tender information is analyzed compared with other tender information demanders. If the bidding competitiveness is greater than or equal to the preset competitiveness threshold, the step of triggering the execution of the target dimension corresponding to the target matching degree, the target demand information matching the target dimension in the multi-dimensional demand information corresponding to the target tender information, and the target capability attribute information matching the target dimension in the multi-dimensional capability attribute information corresponding to the target tender information demander is triggered to analyze the influencing factors of the target matching degree not meeting the matching degree conditions.

[0117] It can be seen that before analyzing the influencing factors why the target matching degree does not meet the matching degree conditions, this optional embodiment can further combine the number of tender information demanders to which the target tender information is pushed, the degree of demand for the target tender information by the target tender information demanders, and the bidding competitiveness of the target tender information demanders compared to other tender information demanders to comprehensively judge whether it is necessary to analyze the influencing factors, which is conducive to improving the reliability of the analysis of the influencing factors, and further conducive to improving the reliability of the generation of the capability attribute optimization strategy.

[0118] In yet another optional embodiment, the above-mentioned capability attribute optimization strategy corresponding to the target bidding information demander generated based on the influencing factors may include:

[0119] According to the target capability attributes that match the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, estimate the difficulty coefficient of adjusting the target capability attributes to weaken or eliminate the influencing factors;

[0120] According to the difficulty coefficient, determine the capability attributes to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander, and analyze the adjustment direction corresponding to the capability attributes to be adjusted;

[0121] According to the adjustment direction corresponding to the capability attribute to be adjusted, a capability attribute optimization strategy corresponding to the capability attribute to be adjusted is generated as the capability attribute optimization strategy corresponding to the target bidding information demander.

[0122] It can be seen that when generating a capability attribute optimization strategy, this optional embodiment can also determine the capability attribute to be adjusted based on the estimated capability attribute adjustment difficulty coefficient, and further generate the capability attribute optimization strategy in combination with the adjustment direction corresponding to the capability attribute to be adjusted, which is beneficial to improving the generation reliability of the capability attribute optimization strategy.

[0123] In yet another optional embodiment, the above-mentioned determining the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander according to the difficulty coefficient includes:

[0124] If the difficulty coefficient is less than or equal to the preset difficulty coefficient threshold, the target ability attribute is determined as the ability attribute to be adjusted; if the difficulty coefficient is greater than the preset difficulty coefficient threshold, the ability attribute to be adjusted is determined from the remaining ability attributes except the target ability attribute.

[0125] In this optional embodiment, further optionally, the above-mentioned determining the capability attribute to be adjusted from the remaining capability attributes except the target capability attribute may include:

[0126] Determine, from the remaining capability attributes except the target capability attribute, a plurality of optional capability attributes with adjustment space;

[0127] For each optional capability attribute, analyze the difficulty of adjusting the optional capability attribute and the degree to which adjusting the optional capability attribute improves the bidding competitiveness of the target bidding information in terms of the demand for the target bidding information, and obtain the selection reference basis corresponding to the optional capability attribute;

[0128] According to the selection reference basis corresponding to all optional capability attributes, the capability attributes to be adjusted are determined from all optional capability attributes.

[0129] It can be seen that this optional embodiment can also intelligently determine the capability attributes to be adjusted according to the size of the capability attribute adjustment difficulty coefficient and the preset difficulty coefficient threshold, which is conducive to improving the reliability of determining the capability attributes to be adjusted. Furthermore, when determining the capability attributes to be adjusted from the remaining capability attributes, it is possible to obtain the selection reference basis corresponding to the remaining capability attributes based on the adjustment difficulty corresponding to the remaining capability attributes and the degree of improvement in the bidding competitiveness of the target bidding information after the adjustment, which is conducive to improving the reliability of determining the capability attributes to be adjusted from the remaining capability attributes, that is: improving the matching degree between the determined capability attributes to be adjusted and the improvement demand for the bidding competitiveness of the target bidding information demander.

[0130] In yet another optional embodiment, the above-mentioned estimated difficulty coefficient of adjusting the target capability attribute to weaken or eliminate the influencing factor may include:

[0131] According to the internal resources of the target bidding information demander, determine the target capability attributes to weaken or eliminate the first difficulty coefficient of the influencing factors;

[0132] According to the internal resources of the target bidding information demander, determine the target capability attributes to weaken or eliminate the second difficulty coefficient of the influencing factors;

[0133] Determine a comprehensive difficulty coefficient according to the first difficulty coefficient and the second difficulty coefficient;

[0134] Based on the current time and the deadline for receiving the bidding documents of the target bidding information, the time difficulty calibration coefficient is determined, and the comprehensive difficulty coefficient is calibrated based on the difficulty calibration coefficient to obtain the difficulty coefficient for adjusting the target ability attributes to weaken or eliminate the influencing factors.

[0135] It can be seen that this optional embodiment can determine the comprehensive difficulty coefficient based on internal and external resources when estimating the difficulty coefficient of adjusting the target ability attribute, and then calibrate the comprehensive difficulty coefficient based on the time difficulty calibration coefficient, which is beneficial to improving the estimation accuracy of the difficulty coefficient of adjusting the target ability attribute.

[0136] In yet another optional embodiment, the method may further include:

[0137] Collect the operation behavior of the target tender information demander after receiving the target tender information, and predict the probability of the target tender information demander bidding on the target tender information based on the operation behavior. If the probability is greater than or equal to a preset probability threshold, analyze the target tender information, and extract the tender document format requirements and multiple key information required for the tender from the target tender information;

[0138] For all key information, all key information shall be divided into first-category key information and second-category key information according to the way in which the key information is obtained. The first-category key information includes key information that can be queried or extracted through public channels;

[0139] According to the requirements of the bidding document format and the first category of key information obtained based on the method of obtaining the first category of key information, the initial bidding documents are organized and provided to the target bidding information demander.

[0140] Further optionally, the method may also include:

[0141] For the second category of key information, the recommended time range for organizing the second category of key information shall be determined based on the acquisition method of the second category of key information, the complexity of organization and the deadline for organization of the bidding documents, and the recommended time range for organizing the second category of key information shall be provided to the target bidding information demanders.

[0142] It should be noted that the bidding decision support system can also manage bidding time nodes to avoid missing important bidding deadlines, such as providing a calendar function module to automatically mark the bidding deadlines of various bidding information and remind the target bidding information demander when it is approaching. In addition, after the target bidding information demander bids, the situation of each bid is recorded and analyzed, such as establishing a bidding record database and generating reports such as bidding success rate, common problems, and improvement suggestions.

[0143] Furthermore, the bidding and tendering decision support system can also perform the following operations:

[0144] Automatically recommend potentially relevant keywords based on historical bidding data and successful cases, such as using data mining and machine learning algorithms to analyze historical data such as those that have been followed, bid, and won, and generate a keyword recommendation list to improve the accuracy of recommendations instead of manually managing keywords; and / or,

[0145] Dynamically adjust the keywords in the bidding information acquisition requirements that match the target bidding information demander to improve the accuracy and comprehensiveness of the bidding information screening; when screening the bidding information based on keywords, introduce natural language processing (NLP) technology to analyze the context of the bidding information and improve the screening accuracy; and / or,

[0146] When recommending bidding information, mark and recommend bidding information with high relevance and high probability of winning the bid. For example, use machine learning algorithms to analyze historical data such as those that have been followed, bid, and won the bid, company resource qualifications, etc., analyze the matching degree of the bidding information, and improve the accuracy of matching the company's business.

[0147] It can be seen that this optional embodiment can also predict the bidding probability of the target bidding information demander based on his or her operational behavior after recommending the target bidding information to the target bidding information demander. If the bidding probability is large, the initial bidding document can be generated according to the key information acquisition method and the bidding document format requirements, which is conducive to assisting the generation of bidding documents and improving the convenience of generating bidding documents. It can also generate a recommended time range for organizing the second type of key information, reducing the situation where the bidding time is missed due to insufficient time and inability to organize a complete bidding document.

[0148] Embodiment 2

[0149] See also Figure 2 , Figure 2 Schematic diagram of the structure of a bidding and tendering decision-making support system based on artificial intelligence disclosed in an embodiment of the present invention. The bidding and tendering decision-making support system can be integrated with a local server or a cloud server, which is not limited in the embodiment of the present invention. Figure 2 As shown, the system may include:

[0150] The channel determination module 201 is used to determine the channel address information corresponding to the bidding information channel that matches the target bidding information demander;

[0151] The information access module 202 is used to analyze the tender information update frequency corresponding to the channel address information based on the historical update information corresponding to the channel address information and the category of tender information publishers settled in the tender information channel; determine the access cycle corresponding to the channel address information in terms of target tender information demand according to the tender information update frequency, and initiate an access operation for the tender information channel according to the access cycle and the channel address information, and the access operation is used to access all current tender information published by the tender information channel;

[0152] The information recommendation module 203 is used to filter out multiple pending tender information from all current tender information, and for each pending tender information, calculate the capability matching degree of the target tender information demand to each pending tender information according to its corresponding multi-dimensional demand information and the multi-dimensional capability attribute information corresponding to the target tender information demander, and, according to the capability matching degree of the target tender information demand to each pending tender information, filter out the target tender information from all pending tender information, and push the target tender information to the target tender information demander; wherein, the capability matching degree of the target tender information demand to the target tender information satisfies the preset matching degree condition.

[0153] It can be seen that implementation Figure 2 The described system can analyze the update frequency of tender information according to multi-dimensional information and determine the appropriate access cycle after determining the address information corresponding to the tender information channel, which is beneficial to improving the timeliness of access to tender information. After accessing multiple tender information in the tender information channel, it first preliminarily screens out pending tender information, and then calculates the capability matching degree corresponding to each pending tender information in terms of tender information demand, and then based on the capability matching degree, screens and recommends tender information whose capability matching degree meets the preset matching degree conditions for the tender information demander, realizes the intelligent screening of tender information, and is beneficial to improving the screening efficiency and screening reliability of tender information.

[0154] In an optional embodiment, if Figure 3 As shown, the system also includes:

[0155] The optimization suggestion module 204 is used to calculate the multi-dimensional matching degree between the target bidding information and the target bidding information demander based on the multi-dimensional demand information corresponding to the target bidding information and the multi-dimensional capability attribute information corresponding to the target bidding information demander. If there is a target matching degree that does not meet the matching degree condition in the multi-dimensional matching degree, then based on the target dimension corresponding to the target matching degree, the target demand information that matches the target dimension in the multi-dimensional demand information corresponding to the target bidding information, and the target capability attribute information that matches the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, analyze the influencing factors of the target matching degree not meeting the matching degree condition, and based on the influencing factors, generate a capability attribute optimization strategy corresponding to the target bidding information demander, and push the capability attribute optimization strategy to the target bidding information demander.

[0156] It can be seen that after recommending suitable target bidding information to the bidding information demander, this optional embodiment can also calculate the multi-dimensional matching degree between the two (that is, the matching degree between multiple dimensions). If there is a target matching degree that does not meet the matching conditions, the corresponding influencing factors are further analyzed intelligently, and a capability attribute optimization strategy is generated based on the analyzed influencing factors, which is conducive to improving the generation accuracy of the capability attribute optimization strategy, and further conducive to further improving the competitiveness of the bidding information demander to the target bidding information, that is: it is conducive to further improving the matching degree between the bidding information demander and the target bidding information.

[0157] In another optional embodiment, the optimization suggestion module 204 is further configured to:

[0158] If the target bidding information is pushed to multiple bidding information demanders, the degree of demand for the target bidding information by the target bidding information demander compared with other bidding information demanders is analyzed. If the degree of demand is greater than or equal to the preset degree threshold, the bidding competitiveness of the target bidding information demander for the target bidding information compared with other bidding information demanders is analyzed. If the bidding competitiveness is greater than or equal to the preset competitiveness threshold, the operation of analyzing the influencing factors of the target matching not meeting the matching conditions is triggered based on the target dimension corresponding to the target matching degree, the target demand information matching the target dimension in the multi-dimensional demand information corresponding to the target bidding information, and the target capability attribute information matching the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander.

[0159] It can be seen that before analyzing the influencing factors why the target matching degree does not meet the matching degree conditions, this optional embodiment can further combine the number of tender information demanders to which the target tender information is pushed, the degree of demand for the target tender information by the target tender information demanders, and the bidding competitiveness of the target tender information demanders compared to other tender information demanders to comprehensively judge whether it is necessary to analyze the influencing factors, which is conducive to improving the reliability of the analysis of the influencing factors, and further conducive to improving the reliability of the generation of the capability attribute optimization strategy.

[0160] In another optional embodiment, the specific manner in which the optimization suggestion module 204 generates the capability attribute optimization strategy corresponding to the target bidding information demander based on the influencing factors includes:

[0161] According to the target capability attributes that match the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, estimate the difficulty coefficient of adjusting the target capability attributes to weaken or eliminate the influencing factors;

[0162] According to the difficulty coefficient, determine the capability attributes to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander, and analyze the adjustment direction corresponding to the capability attributes to be adjusted;

[0163] According to the adjustment direction corresponding to the capability attribute to be adjusted, a capability attribute optimization strategy corresponding to the capability attribute to be adjusted is generated as the capability attribute optimization strategy corresponding to the target bidding information demander.

[0164] It can be seen that when generating a capability attribute optimization strategy, this optional embodiment can also determine the capability attribute to be adjusted based on the estimated capability attribute adjustment difficulty coefficient, and further generate the capability attribute optimization strategy in combination with the adjustment direction corresponding to the capability attribute to be adjusted, which is beneficial to improving the generation reliability of the capability attribute optimization strategy.

[0165] In another optional embodiment, the optimization suggestion module determines the specific manner in which the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander according to the difficulty coefficient 204 includes:

[0166] If the difficulty coefficient is less than or equal to the preset difficulty coefficient threshold, the target capability attribute is determined as the capability attribute to be adjusted; if the difficulty coefficient is greater than the preset difficulty coefficient threshold, the capability attribute to be adjusted is determined from the remaining capability attributes except the target capability attribute;

[0167] The specific manner in which the optimization suggestion module 204 determines the capability attribute to be adjusted from the remaining capability attributes except the target capability attribute includes:

[0168] Determine, from the remaining capability attributes except the target capability attribute, a plurality of optional capability attributes with adjustment space;

[0169] For each optional capability attribute, analyze the difficulty of adjusting the optional capability attribute and the degree to which adjusting the optional capability attribute improves the bidding competitiveness of the target bidding information in terms of the demand for the target bidding information, and obtain the selection reference basis corresponding to the optional capability attribute;

[0170] According to the selection reference basis corresponding to all optional capability attributes, the capability attributes to be adjusted are determined from all optional capability attributes.

[0171] It can be seen that this optional embodiment can also intelligently determine the capability attributes to be adjusted according to the size of the capability attribute adjustment difficulty coefficient and the preset difficulty coefficient threshold, which is conducive to improving the reliability of determining the capability attributes to be adjusted. Furthermore, when determining the capability attributes to be adjusted from the remaining capability attributes, it is possible to obtain the selection reference basis corresponding to the remaining capability attributes based on the adjustment difficulty corresponding to the remaining capability attributes and the degree of improvement in the bidding competitiveness of the target bidding information after the adjustment, which is conducive to improving the reliability of determining the capability attributes to be adjusted from the remaining capability attributes, that is: improving the matching degree between the determined capability attributes to be adjusted and the improvement demand for the bidding competitiveness of the target bidding information demander.

[0172] In yet another optional embodiment, the specific manner in which the optimization suggestion module 204 estimates the difficulty coefficient of adjusting the target capability attribute to weaken or eliminate the influencing factor includes:

[0173] According to the internal resources of the target bidding information demander, determine the target capability attributes to weaken or eliminate the first difficulty coefficient of the influencing factors;

[0174] According to the internal resources of the target bidding information demander, determine the target capability attributes to weaken or eliminate the second difficulty coefficient of the influencing factors;

[0175] Determine a comprehensive difficulty coefficient according to the first difficulty coefficient and the second difficulty coefficient;

[0176] Based on the current time and the deadline for receiving the bidding documents of the target bidding information, the time difficulty calibration coefficient is determined, and the comprehensive difficulty coefficient is calibrated based on the difficulty calibration coefficient to obtain the difficulty coefficient for adjusting the target ability attributes to weaken or eliminate the influencing factors.

[0177] It can be seen that this optional embodiment can determine the comprehensive difficulty coefficient based on internal and external resources when estimating the difficulty coefficient of adjusting the target ability attribute, and then calibrate the comprehensive difficulty coefficient based on the time difficulty calibration coefficient, which is beneficial to improving the estimation accuracy of the difficulty coefficient of adjusting the target ability attribute.

[0178] In yet another optional embodiment, Figure 3 As shown, the system further includes a bidding assistance module 205, wherein:

[0179] The bidding auxiliary module 205 is used to collect the operation behavior of the target bidding information demander after receiving the target bidding information, and predict the probability of bidding the target bidding information demander based on the operation behavior. If the probability is greater than or equal to a preset probability threshold, the target bidding information is analyzed, and the bidding document format requirements and multiple key information required for bidding are extracted from the target bidding information; for all key information, all key information is divided into first-category key information and second-category key information according to the key information acquisition method, and the first-category key information includes key information that can be queried or extracted through public channels; according to the bidding document format requirements and the first-category key information acquired based on the acquisition method of the first-category key information, the initial bidding document is sorted out, and the initial bidding document is provided to the target bidding information demander;

[0180] In addition, the bidding assistance module 205 is also used to determine the recommended time range for organizing the second type of key information based on the acquisition method, organization complexity and bidding document organization deadline of the second type of key information, and provide the recommended time range for organizing the second type of key information to the target bidding information demander.

[0181] It can be seen that this optional embodiment can also predict the bidding probability of the target bidding information demander based on his or her operational behavior after recommending the target bidding information to the target bidding information demander. If the bidding probability is large, the initial bidding document can be generated according to the key information acquisition method and the bidding document format requirements, which is conducive to assisting the generation of bidding documents and improving the convenience of generating bidding documents. It can also generate a recommended time range for organizing the second type of key information, reducing the situation where the bidding time is missed due to insufficient time and inability to organize a complete bidding document.

[0182] Embodiment 3

[0183] See also Figure 4 , Figure 4 is a schematic diagram of the structure of another bidding and tendering decision-making support system based on artificial intelligence disclosed in an embodiment of the present invention. The bidding and tendering decision-making support system can be integrated with a local server or a cloud server, which is not limited in the embodiment of the present invention. Figure 4 As shown, the system may include:

[0184] A memory 301 storing executable program codes;

[0185] a processor 302 coupled to a memory;

[0186] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in any one of the artificial intelligence-based bidding decision-making assistance methods described in the first embodiment.

[0187] Embodiment 4

[0188] An embodiment of the present invention discloses a computer storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute any step of the artificial intelligence-based bidding and tendering decision-making assistance method described in Embodiment 1.

[0189] Embodiment 5

[0190] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of any one of the artificial intelligence-based bidding and tendering decision-making assistance methods described in Example 1.

[0191] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0192] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, a magnetic disk storage, a magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0193] Finally, it should be noted that the artificial intelligence-based bidding and tendering decision-making support method and system disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A bidding and tendering decision-making assistance method based on artificial intelligence, characterized in that: The method comprises: Determine the channel address information corresponding to the bidding information channel that matches the target bidding information demander; Based on the historical update information corresponding to the channel address information and the category of the tender information publisher settled in the tender information channel, analyzing the tender information update frequency corresponding to the channel address information; Determine the access cycle corresponding to the channel address information of the target tender information demand according to the tender information update frequency, and initiate an access operation for the tender information channel according to the access cycle and the channel address information, wherein the access operation is used to access all current tender information published by the tender information channel; Filtering out a plurality of pending tender information from all the current tender information, and for each of the pending tender information, calculating the degree of matching of the target tender information demand with the capability corresponding to each of the pending tender information according to the corresponding multi-dimensional demand information and the multi-dimensional capability attribute information corresponding to the target tender information demander; According to the capability matching degree of the target bidding information demand to each of the pending bidding information, the target bidding information is screened out from all the pending bidding information, and the target bidding information is pushed to the target bidding information demander; wherein the capability matching degree of the target bidding information demand to the target bidding information satisfies a preset matching degree condition.

2. The bidding and tendering decision-making auxiliary method based on artificial intelligence according to claim 1 is characterized in that: After pushing the target bidding information to the target bidding information demander, the method further includes: Based on the multi-dimensional demand information corresponding to the target bidding information and the multi-dimensional capability attribute information corresponding to the target bidding information demander, the multi-dimensional matching degree between the target bidding information and the target bidding information demander is calculated. If there is a target matching degree that does not meet the matching degree condition in the multi-dimensional matching degree, then based on the target dimension corresponding to the target matching degree, the target demand information that matches the target dimension in the multi-dimensional demand information corresponding to the target bidding information, and the target capability attribute information that matches the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, the influencing factors of the target matching degree not meeting the matching degree condition are analyzed, and based on the influencing factors, a capability attribute optimization strategy corresponding to the target bidding information demander is generated, and the capability attribute optimization strategy is pushed to the target bidding information demander.

3. The bidding and tendering decision-making auxiliary method based on artificial intelligence according to claim 2 is characterized in that: If there is a target matching degree that does not satisfy the matching degree condition in the multidimensional matching degree, before analyzing the influencing factors that the target matching degree does not satisfy the matching degree condition based on the target dimension corresponding to the target matching degree, the target demand information that matches the target dimension in the multidimensional demand information corresponding to the target bidding information, and the target capability attribute information that matches the target dimension in the multidimensional capability attribute information corresponding to the target bidding information demander, the method further includes: If the target tender information is pushed to multiple tender information demanders, the degree of demand for the target tender information by the target tender information demander compared with other tender information demanders is analyzed. If the degree of demand is greater than or equal to the preset degree threshold, the bidding competitiveness of the target tender information demander for the target tender information is analyzed compared with the other tender information demanders. If the bidding competitiveness is greater than or equal to the preset competitiveness threshold, the step of analyzing the influencing factors of the target matching degree not satisfying the matching degree condition based on the target dimension corresponding to the target matching degree, the target demand information matching the target dimension in the multi-dimensional demand information corresponding to the target tender information, and the target capability attribute information matching the target dimension in the multi-dimensional capability attribute information corresponding to the target tender information demander is triggered.

4. The bidding and tendering decision-making auxiliary method based on artificial intelligence according to claim 3 is characterized in that: The generating, based on the influencing factors, a capability attribute optimization strategy corresponding to the target bidding information demander includes: According to the target capability attribute that matches the target dimension in the multi-dimensional capability attribute information corresponding to the target bidding information demander, estimate the difficulty coefficient of adjusting the target capability attribute to weaken or eliminate the influencing factor; According to the difficulty coefficient, determining the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander, and analyzing the adjustment direction corresponding to the capability attribute to be adjusted; According to the adjustment direction corresponding to the capability attribute to be adjusted, a capability attribute optimization strategy corresponding to the capability attribute to be adjusted is generated as the capability attribute optimization strategy corresponding to the target bidding information demander.

5. The bidding and tendering decision-making auxiliary method based on artificial intelligence according to claim 4 is characterized in that: The step of determining, according to the difficulty coefficient, the capability attribute to be adjusted in the multi-dimensional capability attribute information corresponding to the target bidding information demander includes: If the difficulty coefficient is less than or equal to the preset difficulty coefficient threshold, the target capability attribute is determined as the capability attribute to be adjusted; if the difficulty coefficient is greater than the preset difficulty coefficient threshold, the capability attribute to be adjusted is determined from the remaining capability attributes except the target capability attribute; The step of determining the capability attribute to be adjusted from the remaining capability attributes except the target capability attribute includes: Determining a plurality of optional capability attributes having adjustment space from the remaining capability attributes except the target capability attribute; For each of the optional capability attributes, analyzing the difficulty of adjusting the optional capability attribute and the degree to which adjusting the optional capability attribute improves the bidding competitiveness of the target bidding information in terms of the demand of the target bidding information, and obtaining a selection reference basis corresponding to the optional capability attribute; According to the selection references corresponding to all the optional capability attributes, the capability attributes to be adjusted are determined from all the optional capability attributes.

6. The bidding and tendering decision-making auxiliary method based on artificial intelligence according to claim 4 is characterized in that: The estimating and adjusting the target capability attribute to reduce or eliminate the difficulty coefficient of the influencing factor includes: Determining the target capability attribute to weaken or eliminate the first difficulty coefficient of the influencing factor according to the internal resources of the target tender information demander; Determining the target capability attribute to weaken or eliminate the second difficulty coefficient of the influencing factor according to the internal resources of the target bidding information demander; Determining a comprehensive difficulty coefficient according to the first difficulty coefficient and the second difficulty coefficient; Based on the current time and the deadline for receiving the bidding documents of the target bidding information, the time difficulty calibration coefficient is determined, and the comprehensive difficulty coefficient is calibrated based on the difficulty calibration coefficient to obtain the difficulty coefficient for adjusting the target ability attribute to weaken or eliminate the influencing factors.

7. The bidding and tendering decision-making auxiliary method based on artificial intelligence according to any one of claims 1 to 6, characterized in that: The method further comprises: Collecting the operation behavior of the target tender information demander after receiving the target tender information, predicting the probability of the target tender information demander bidding on the target tender information based on the operation behavior, and if the probability is greater than or equal to a preset probability threshold, analyzing the target tender information, and extracting the tender document format requirements and multiple key information required for the tender from the target tender information; For all the key information, all the key information is divided into first-category key information and second-category key information according to the acquisition method of the key information, wherein the first-category key information includes key information that can be queried or extracted through public channels; Arranging the initial bidding document according to the bidding document format requirements and the first type of key information obtained based on the way of obtaining the first type of key information, and providing the initial bidding document to the target bidding information demander; And, the method further comprises: For the second category of key information, the recommended time range for organizing the second category of key information is determined based on the acquisition method, organization complexity and deadline for organizing the tender documents of the second category of key information, and the recommended time range for organizing the second category of key information is provided to the target tender information demander.

8. An artificial intelligence-based bidding decision-making support system, characterized in that: The system comprises: A channel determination module is used to determine the channel address information corresponding to the bidding information channel that matches the target bidding information demander; An information access module is used to analyze the tender information update frequency corresponding to the channel address information based on the historical update information corresponding to the channel address information and the category of tender information publishers settled in the tender information channel; determine the access cycle corresponding to the channel address information of the target tender information demand according to the tender information update frequency, and initiate an access operation for the tender information channel according to the access cycle and the channel address information, wherein the access operation is used to access all current tender information published by the tender information channel; An information recommendation module is used to filter out multiple pending tender information from all the current tender information, and for each pending tender information, calculate the capability matching degree of the target tender information demand to each pending tender information according to its corresponding multi-dimensional demand information and the multi-dimensional capability attribute information corresponding to the target tender information demander, and, according to the capability matching degree of the target tender information demand to each pending tender information, filter out the target tender information from all the pending tender information, and push the target tender information to the target tender information demander; wherein, the capability matching degree of the target tender information demand to the target tender information meets a preset matching condition.

9. An artificial intelligence-based bidding decision-making support system, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the artificial intelligence-based bidding and tendering decision-making assistance method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, which, when called, are used to execute the artificial intelligence-based bidding and tendering decision-making assistance method as described in any one of claims 1 to 7.

Images