Bidding purchasing management method and device and computer equipment

Abstract

The invention relates to a bidding and tendering purchase management method and device and computer equipment. The method comprises the following steps: obtaining bid invitation demand information and bid invitation condition information of each bid invitation theme, and identifying bid invitation announcement information and adaptive enterprises of each bid invitation theme; sending bid invitation announcement information of each bid invitation theme to each adaptive enterprise and each non-adaptive enterprise, screening bidding information of each intention enterprise based on bidding information and bid invitation condition information of each enterprise of the bid invitation theme, and evaluating an objective score value and a subjective score value of the bidding information of each intention enterprise; and on the basis of the objective score value of the bidding information of each intentional enterprise and the subjective score value of the bidding information of each intentional enterprise, screening an enterprise corresponding to the bidding information of each target intentional enterprise corresponding to the bidding theme as a target purchasing enterprise of the bidding theme. By adopting the method, the bidding and tendering purchasing accuracy of multiple bidding themes can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and big data management technology, and in particular to a method, device and computer equipment for managing bidding and procurement. Background Art

[0002] With the increase in bidding projects and the expansion of bidding scope, the number of bidding topics and bidding enterprises has gradually increased. Especially when the same enterprise needs to conduct bidding and procurement management for multiple bidding topics, it often requires a large number of staff, as well as multi-cycle and long-term repetitive work, which makes the efficiency of bidding and procurement management for multiple bidding topics low. This has a great impact on the actual project development, technology research and development, and resource coordination of the enterprise. Therefore, how to improve the efficiency of bidding and procurement is the current research focus.

[0003] The traditional technology improves the efficiency of bidding and procurement by appointing multiple bidding companies to manage the bidding process for different bidding topics, and appointing professional bidding reviewers to review each bidding information, thereby improving the efficiency of bidding and procurement. However, this method requires a lot of manpower costs, resulting in high cost resources, and manual review is prone to deviations and requires re-examination, resulting in low accuracy in bidding and procurement for multiple bidding topics. Summary of the invention

[0004] Based on this, it is necessary to provide a bidding and procurement management method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical issues.

[0005] In a first aspect, the present application provides a method for managing bidding and procurement, including: Acquire the bidding requirement information of each bidding theme and the bidding condition information of each bidding theme, and identify the bidding announcement information of each bidding theme and the matching enterprise of each bidding theme based on the bidding requirement information of each bidding theme; Through the preset bidding transmission channels of each adapted enterprise and the preset bidding transmission channels of each non-adapted enterprise, the bidding announcement information of each bidding topic is sent to each adapted enterprise and each non-adapted enterprise, and the enterprise bidding information of each enterprise for each bidding topic is collected; For each bidding theme, based on the bidding information of each enterprise of the bidding theme and the bidding condition information of the bidding theme, the bidding information of each intended enterprise is screened from the bidding information of each enterprise, and the bidding information of each intended enterprise is objectively scored through the bidding evaluation network to obtain the objective scoring value of the bidding information of each intended enterprise; receiving expert review opinions on the bidding information of each of the intended enterprises, and generating subjective scoring values ​​for the bidding information of each of the intended enterprises based on the expert review opinions on the bidding information of each of the intended enterprises; Based on the objective scoring values ​​of the bidding information of each of the intended enterprises and the subjective scoring values ​​of the bidding information of each of the intended enterprises, the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme are screened as the target purchasing enterprises of the bidding theme.

[0006] Optionally, the identifying the tender announcement information of each tender theme and the suitable enterprise of each tender theme based on the tender demand information of each tender theme includes: Obtain a tender notice template, and for each tender subject, identify the requirement type of each tender requirement topic and the requirement content of each tender requirement topic based on the tender requirement information of the tender subject; Identify the location information corresponding to each requirement type of the tender announcement template, and fill the tender requirement title of each requirement type and the requirement content of the tender requirement title of each requirement type into the tender announcement template to obtain the tender requirement information of the tender subject; Through the text recognition network, the qualification requirement information in the requirement content of the bidding requirement topic of the enterprise qualification requirement type is identified, and the enterprises corresponding to the enterprise qualification information that are adapted to each of the qualification requirement information are screened in the Internet database or the cooperative enterprise database as the adapted enterprises of the bidding subject.

[0007] Optionally, sending the tender announcement information of each tender subject to each of the adapted enterprises and each of the non-adapted enterprises through the preset tender transmission channels of each of the adapted enterprises and the preset tender transmission channels of each of the non-adapted enterprises includes: For each bidding theme, the enterprise qualification information of each suitable enterprise of the bidding theme and the enterprise fitness between the qualification requirement information of the bidding theme are calculated by using the fitness algorithm, and based on the enterprise fitness of each suitable enterprise, each suitable enterprise is divided into enterprise groups of each fitness level; In the sending database, identifying the bidding transmission channels of each adaptation level and the bidding transmission channels without adaptation level, and sending the bidding announcement information of the bidding subject to the enterprise group of each adaptation level of the bidding subject through the bidding transmission channels of each adaptation level; The bidding announcement information of the bidding subject is sent to the bidding transmission channels of each non-adaptable enterprise through the bidding transmission channel without adaptation level.

[0008] Optionally, the step of screening the bidding information of each intended enterprise from the bidding information of each enterprise based on the bidding information of each enterprise and the bidding condition information of the bidding subject includes: Splitting the bidding condition information of the bidding subject into condition contents of each bidding condition type, and identifying the bidding category corresponding to each bidding condition type in the bidding database; For each enterprise bidding information, the enterprise bidding information is split into bidding contents of each bidding category, and the matching degree between the condition content of each bidding condition type and the bidding contents of the bidding category corresponding to each bidding condition type is respectively identified through a semantic recognition network; When there is no matching degree lower than the matching degree threshold, the enterprise bidding information is used as the intended enterprise bidding information of the bidding subject.

[0009] Optionally, the bidding evaluation network is used to objectively score the bidding information of each intended enterprise to obtain an objective score value of the bidding information of each intended enterprise, including: For each intended enterprise bidding information, in the bidding category of the intended enterprise bidding information, the objective bidding content of the objective bidding category of the objective type is screened, and based on the objective type of each objective bidding category, the objective scoring index corresponding to each objective type is searched in the index database; Inputting the objective bidding contents of the objective bidding categories of each objective type and the objective scoring indicators corresponding to each objective type into the bidding evaluation network, and identifying the sub-score values ​​of the objective bidding categories of each objective type; Based on the sub-score values ​​of the objective bidding category of each objective type and the weight value of the objective bidding category of each objective type, the objective score value of the bidding information of the intended enterprise is determined.

[0010] Optionally, generating a subjective scoring value for the bidding information of each of the intended enterprises based on the expert review opinions of the bidding information of each of the intended enterprises includes: For each intended enterprise bidding information, the expert review opinions of the intended enterprise bidding information are split into sub-expert review contents of subjective bidding categories of each subjective type, and the review semantic information of each sub-expert review content is identified through the semantic recognition network; In the indicator database, query the subjective scoring indicator of each subjective type, and identify the indicator semantic information corresponding to each indicator value of each subjective scoring indicator through the semantic recognition network; For each subjective type, based on the review semantic information of the sub-expert review content of the subjective bidding category of the subjective type and the indicator semantic information corresponding to each indicator value in the subjective scoring indicator of the subjective type, the similarity between the sub-expert review content and each indicator value is calculated through a semantic similarity algorithm, and the indicator value corresponding to the maximum similarity is selected as the target indicator value of the sub-expert review content; Based on the target index value of the sub-expert review content of each subjective bidding category of each subjective type and the weight value of each subjective bidding category of each subjective type, the subjective scoring value of the bidding information of the intended enterprise is determined.

[0011] Optionally, the step of selecting the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme as the target purchasing enterprise of the bidding theme based on the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise includes: Based on the adaptation level of the enterprise corresponding to each of the intended enterprise bidding information, the objective score value of each intended enterprise bidding information and the subjective score value of each intended enterprise bidding information are weighted and adjusted to obtain the adaptation objective score value of each intended enterprise bidding information and the adaptation subjective score value of each intended enterprise bidding information; Based on a preset first weight value of the objective scoring value and a preset second weight value of the subjective scoring value, weighted sum processing is performed on the adapted objective scoring value of each intended enterprise bidding information and the adapted subjective scoring value of each intended enterprise bidding information to obtain a target scoring value of each intended enterprise bidding information; According to the target score from high to low, the enterprises corresponding to the bidding information of each intended enterprise are sorted to obtain an enterprise sequence, and the number of purchasing enterprises of the bidding subject is collected; According to the order of the enterprise sequence from front to back, enterprises with the same number of purchasing enterprises as the bidding subject are selected as the target purchasing enterprises of the bidding subject.

[0012] In a second aspect, the present application also provides a bidding and procurement management device, including: An acquisition module, used to acquire the tender demand information of each tender theme and the tender condition information of each tender theme, and identify the tender announcement information of each tender theme and the adaptable enterprise of each tender theme based on the tender demand information of each tender theme; A sending module, used to send the bidding announcement information of each bidding topic to each of the adapted enterprises and each of the non-adapted enterprises through the preset bidding transmission channels of each adapted enterprise and the preset bidding transmission channels of each non-adapted enterprise, and collect the enterprise bidding information of each enterprise for each bidding topic; The scoring module is used to screen the bidding information of each intended enterprise from the bidding information of each enterprise based on the bidding information of each enterprise and the bidding condition information of the bidding theme for each bidding theme, and objectively score the bidding information of each intended enterprise through the bidding evaluation network to obtain the objective score value of the bidding information of each intended enterprise; A generating module, used for receiving the expert review opinions of the bidding information of each of the intended enterprises, and generating a subjective score value of the bidding information of each of the intended enterprises based on the expert review opinions of the bidding information of each of the intended enterprises; The screening module is used to screen the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme as the target purchasing enterprise of the bidding theme based on the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise.

[0013] Optionally, the acquisition module is specifically used to: Obtain a tender notice template, and for each tender subject, identify the requirement type of each tender requirement topic and the requirement content of each tender requirement topic based on the tender requirement information of the tender subject; Identify the location information corresponding to each requirement type of the tender announcement template, and fill the tender requirement title of each requirement type and the requirement content of the tender requirement title of each requirement type into the tender announcement template to obtain the tender requirement information of the tender subject; Through the text recognition network, the qualification requirement information in the requirement content of the bidding requirement topic of the enterprise qualification requirement type is identified, and the enterprises corresponding to the enterprise qualification information that are adapted to each of the qualification requirement information are screened in the Internet database or the cooperative enterprise database as the adapted enterprises of the bidding subject.

[0014] Optionally, the sending module is specifically used to: For each bidding theme, the enterprise qualification information of each suitable enterprise of the bidding theme and the enterprise fitness between the qualification requirement information of the bidding theme are calculated by using the fitness algorithm, and based on the enterprise fitness of each suitable enterprise, each suitable enterprise is divided into enterprise groups of each fitness level; In the sending database, identifying the bidding transmission channels of each adaptation level and the bidding transmission channels without adaptation level, and sending the bidding announcement information of the bidding subject to the enterprise group of each adaptation level of the bidding subject through the bidding transmission channels of each adaptation level; The bidding announcement information of the bidding subject is sent to the bidding transmission channels of each non-adaptable enterprise through the bidding transmission channel without adaptation level.

[0015] Optionally, the scoring module is specifically used to: Splitting the bidding condition information of the bidding subject into condition contents of each bidding condition type, and identifying the bidding category corresponding to each bidding condition type in the bidding database; For each enterprise bidding information, the enterprise bidding information is split into bidding contents of each bidding category, and the matching degree between the condition content of each bidding condition type and the bidding contents of the bidding category corresponding to each bidding condition type is respectively identified through a semantic recognition network; When there is no matching degree lower than the matching degree threshold, the enterprise bidding information is used as the intended enterprise bidding information of the bidding subject.

[0016] Optionally, the scoring module is specifically used to: For each intended enterprise bidding information, in the bidding category of the intended enterprise bidding information, the objective bidding content of the objective bidding category of the objective type is screened, and based on the objective type of each objective bidding category, the objective scoring index corresponding to each objective type is searched in the index database; Inputting the objective bidding contents of the objective bidding categories of each objective type and the objective scoring indicators corresponding to each objective type into the bidding evaluation network, and identifying the sub-score values ​​of the objective bidding categories of each objective type; Based on the sub-score values ​​of the objective bidding category of each objective type and the weight value of the objective bidding category of each objective type, the objective score value of the bidding information of the intended enterprise is determined.

[0017] Optionally, the generating module is specifically used for: For each intended enterprise bidding information, the expert review opinions of the intended enterprise bidding information are split into sub-expert review contents of subjective bidding categories of each subjective type, and the review semantic information of each sub-expert review content is identified through the semantic recognition network; In the indicator database, query the subjective scoring indicator of each subjective type, and identify the indicator semantic information corresponding to each indicator value of each subjective scoring indicator through the semantic recognition network; For each subjective type, based on the review semantic information of the sub-expert review content of the subjective bidding category of the subjective type and the indicator semantic information corresponding to each indicator value in the subjective scoring indicator of the subjective type, the similarity between the sub-expert review content and each indicator value is calculated through a semantic similarity algorithm, and the indicator value corresponding to the maximum similarity is selected as the target indicator value of the sub-expert review content; Based on the target index value of the sub-expert review content of each subjective bidding category of each subjective type and the weight value of each subjective bidding category of each subjective type, the subjective scoring value of the bidding information of the intended enterprise is determined.

[0018] Optionally, the screening module is specifically used to: Based on the adaptation level of the enterprise corresponding to each of the intended enterprise bidding information, the objective score value of each intended enterprise bidding information and the subjective score value of each intended enterprise bidding information are weighted and adjusted to obtain the adaptation objective score value of each intended enterprise bidding information and the adaptation subjective score value of each intended enterprise bidding information; Based on a preset first weight value of the objective scoring value and a preset second weight value of the subjective scoring value, weighted sum processing is performed on the adapted objective scoring value of each intended enterprise bidding information and the adapted subjective scoring value of each intended enterprise bidding information to obtain a target scoring value of each intended enterprise bidding information; According to the target score from high to low, the enterprises corresponding to the bidding information of each intended enterprise are sorted to obtain an enterprise sequence, and the number of purchasing enterprises of the bidding subject is collected; According to the order of the enterprise sequence from front to back, enterprises with the same number of purchasing enterprises as the bidding subject are selected as the target purchasing enterprises of the bidding subject.

[0019] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0021] The above-mentioned bidding and tendering procurement management method, device and computer equipment obtain the bidding demand information of each bidding theme and the bidding condition information of each bidding theme, and identify the bidding announcement information of each bidding theme and the matching enterprises of each bidding theme based on the bidding demand information of each bidding theme; send the bidding announcement information of each bidding theme to each matching enterprise and each non-matching enterprise through the preset bidding transmission channel of each matching enterprise and the bidding transmission channel of each non-matching enterprise, and collect the enterprise bidding information of each enterprise for each bidding theme; for each bidding theme, based on the bidding information of each enterprise of the bidding theme and the bidding condition information of each bidding theme, The bidding condition information of the subject is selected, and the bidding information of each intended enterprise is screened from the bidding information of each enterprise, and the bidding information of each intended enterprise is objectively scored through the bidding evaluation network to obtain the objective scoring value of each intended enterprise bidding information; the expert review opinions of each intended enterprise bidding information are received, and based on the expert review opinions of each intended enterprise bidding information, the subjective scoring value of each intended enterprise bidding information is generated; based on the objective scoring value of each intended enterprise bidding information and the subjective scoring value of each intended enterprise bidding information, the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding subject are screened as the target purchasing enterprises of the bidding subject. This scheme generates the bidding power consumption information corresponding to the bidding demand by analyzing the bidding demand of each bidding theme, and based on the adaptable enterprises and non-adaptable enterprises of each bidding theme, through the preset bidding transmission channels of each adaptable enterprise and the preset bidding transmission channels of each non-adaptable enterprise, the bidding announcement information of each bidding theme is sent to each adaptable enterprise and each non-adaptable enterprise, which not only improves the accuracy of the issuance of bidding demand, but also effectively saves channel costs and avoids the problem of inefficiency and low accuracy of unified issuance. Then, after obtaining the enterprise bidding information of each enterprise for each bidding theme, this scheme screens the bidding information of the intended enterprises through the bidding condition information of each bidding theme, and identifies the scoring value of the bidding information of each intended enterprise through objective scoring and subjective scoring of expert review opinions, avoiding the problems of inefficiency, low accuracy and high repetition rate of manual scoring, and this method can also effectively improve the scoring efficiency and scoring accuracy of different bidding themes. So as to improve the accuracy of screening the target purchasing enterprises of each bidding theme. Thereby comprehensively improving the bidding and procurement accuracy of multiple bidding themes. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flowchart of a method for managing bidding and procurement in one embodiment; Figure 2 A flowchart of an example of management of bidding and procurement in an embodiment; Figure 3 A structural block diagram of a management device for bidding and procurement in one embodiment; Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0025] The management method of bidding and tendering procurement provided in the embodiment of the present application can be applied to the application environment corresponding to the bidding and tendering procurement platform. Among them, the method can be applied to a terminal, can be applied to a server, can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, etc. Among them, the terminal generates the bidding power consumption information corresponding to the bidding demand by analyzing the bidding demand of each bidding theme, and based on the adaptable enterprises and non-adaptable enterprises of each bidding theme, the bidding announcement information of each bidding theme is sent to each of the adaptable enterprises and each of the non-adaptable enterprises through the preset bidding transmission channels of each adaptable enterprise and the preset bidding transmission channels of each non-adaptable enterprise, which not only improves the accuracy of the issuance of bidding demand, but also can effectively save channel costs and avoid the problem of inefficiency and low accuracy of unified issuance. Then, after obtaining the enterprise bidding information of each enterprise for each bidding theme, this solution screens the bidding information of the intended enterprises through the bidding condition information of each bidding theme, and identifies the scoring value of the bidding information of each intended enterprise through objective scoring and subjective scoring of expert review opinions, avoiding the problems of inefficiency, low precision and high repetition rate of manual scoring, and this method can also effectively improve the scoring efficiency and scoring accuracy of different bidding themes. In order to improve the accuracy of screening the target purchasing enterprises of each bidding theme, the bidding and procurement accuracy of multiple bidding themes is comprehensively improved.

[0026] In an exemplary embodiment, Figure 1 As shown, a bidding and tendering procurement management method is provided, which is described by taking the method applied to a terminal as an example, and includes the following steps S101 to S105. Among them: Step S101, obtaining the bidding requirement information of each bidding theme and the bidding condition information of each bidding theme, and based on the bidding requirement information of each bidding theme, identifying the bidding announcement information of each bidding theme and the matching enterprises of each bidding theme.

[0027] In this embodiment, the terminal responds to the bidding data uploaded by the bidding enterprise on the bidding procurement platform, and obtains the bidding demand information of each bidding theme and the bidding condition information of each bidding theme. Among them, the bidding demand information includes the project tasks that need to be bid for this bidding, the enterprise qualifications required for this bidding, and the project content that the enterprise needs to execute. The bidding condition information of each bidding theme includes the condition content of the bidding condition type, wherein the bidding condition type includes but is not limited to project experience condition type, team building condition type, R&D example condition type, honorary award condition type, paper journal condition type, and financial strength condition type, etc. Among them, each bidding condition type corresponds to a bidding category in each bidding category that an enterprise needs to fill in the bidding document. Then, based on the bidding demand information of each bidding theme, the terminal identifies the bidding announcement information of each bidding theme and the matching enterprise of each bidding theme. Among them. The terminal presets a bidding announcement template, and then the terminal fills the demand content of each demand type in each bidding theme into the position information corresponding to each demand type in the bidding announcement template, and obtains the bidding announcement information of each bidding theme. The specific process of identifying the matching enterprise of each bidding theme will be described in detail later.

[0028] Step S102, through the preset bidding transmission channels of each adapted enterprise and the preset bidding transmission channels of each non-adapted enterprise, the bidding announcement information of each bidding topic is sent to each adapted enterprise and each non-adapted enterprise, and the enterprise bidding information of each enterprise for each bidding topic is collected.

[0029] In this embodiment, the terminal sends the tender announcement information of each tender topic to each adapted enterprise and each non-adapted enterprise through the preset tender transmission channel of each adapted enterprise and the preset tender transmission channel of each non-adapted enterprise, and collects the enterprise bidding information of each enterprise for each tender topic.

[0030] Among them, the bidding transmission channel includes multiple transmission channels, including but not limited to telephone channels, email channels, public announcement channels, on-site personnel channels, SMS channels, Internet information channels and other channels. Among them, the adaptable enterprises can be divided into adaptable enterprises with different adaptation levels. The specific division process will be explained in detail later. Non-adaptable enterprises are all non-adaptable enterprises in the industry involved in the bidding subject.

[0031] Step S103, for each bidding theme, based on the bidding information of each enterprise in the bidding theme and the bidding condition information of the bidding theme, the bidding information of each intended enterprise is screened from the bidding information of each enterprise, and the bidding information of each intended enterprise is objectively scored through the bidding evaluation network to obtain the objective scoring value of the bidding information of each intended enterprise.

[0032] In this embodiment, for each bidding theme, the terminal screens the bidding information of each intended enterprise from the bidding information of each enterprise based on the bidding information of each enterprise and the bidding condition information of the bidding theme, and objectively scores the bidding information of each intended enterprise through the bidding evaluation network to obtain the objective score value of the bidding information of each intended enterprise. The specific screening process will be described in detail later, and the bidding evaluation network is a neural network based on deep learning. The specific scoring process will be described in detail later.

[0033] Step S104, receiving expert review opinions on the bidding information of each intended enterprise, and generating a subjective score value for the bidding information of each intended enterprise based on the expert review opinions on the bidding information of each intended enterprise.

[0034] In this embodiment, the terminal receives the expert review opinions of the bidding information of each intended enterprise, and generates a subjective score value of the bidding information of each intended enterprise based on the expert review opinions of the bidding information of each intended enterprise. Before receiving the expert review opinions, the terminal sends the bidding information of each intended enterprise to the expert review panel, and then responds to the expert review panel's expert opinion summary feedback operation to obtain the expert review opinions of the bidding information of each intended enterprise. The specific process of generating the subjective score value of the bidding information of each intended enterprise will be described in detail later.

[0035] Step S105, based on the objective scoring values ​​of the bidding information of each intended enterprise and the subjective scoring values ​​of the bidding information of each intended enterprise, the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme are selected as the target purchasing enterprises of the bidding theme.

[0036] In this embodiment, the terminal selects the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme as the target purchasing enterprises of the bidding theme based on the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise. The number of each target purchasing enterprise is the number of enterprises required to be purchased by each bidding theme. The specific process of selecting the enterprises corresponding to the bidding information of each target intended enterprise corresponding to each bidding theme will be described in detail later.

[0037] Based on the above scheme, by analyzing the bidding requirements of each bidding theme, the bidding power consumption information corresponding to the bidding requirements is generated, and based on the adaptable enterprises and non-adaptable enterprises of each bidding theme, the bidding announcement information of each bidding theme is sent to each adaptable enterprise and each non-adaptable enterprise through the preset bidding transmission channels of each adaptable enterprise and the preset bidding transmission channels of each non-adaptable enterprise, which not only improves the accuracy of the issuance of bidding requirements, but also effectively saves channel costs and avoids the problem of inefficiency and low accuracy of unified issuance. Then, after obtaining the enterprise bidding information of each enterprise for each bidding theme, this scheme screens the bidding information of the intended enterprises through the bidding condition information of each bidding theme, and identifies the scoring value of the bidding information of each intended enterprise through objective scoring and subjective scoring of expert review opinions, avoiding the problems of inefficiency, low accuracy and high repetition rate of manual scoring, and this method can also effectively improve the scoring efficiency and scoring accuracy of different bidding themes. So as to improve the accuracy of screening the target purchasing enterprises of each bidding theme. Thereby comprehensively improving the bidding and procurement accuracy of multiple bidding themes.

[0038] Optionally, based on the bidding demand information of each bidding theme, identify the bidding announcement information of each bidding theme and the compatible enterprises of each bidding theme, including: obtaining a bidding announcement template, and for each bidding theme, identifying the demand type of each bidding demand topic and the demand content of each bidding demand topic based on the bidding demand information of the bidding theme; identifying the location information corresponding to each demand type of the bidding announcement template, and filling the bidding demand topic of each demand type and the demand content of the bidding demand topic of each demand type into the bidding announcement template to obtain the bidding demand information of the bidding theme; identifying each qualification demand information in the demand content of the bidding demand topic of the enterprise qualification demand type through a text recognition network, and screening enterprises corresponding to the enterprise qualification information that are compatible with each qualification demand information in the Internet database or the cooperative enterprise database as the compatible enterprises of the bidding theme.

[0039] In this embodiment, the terminal obtains a tender announcement template, and for each tender topic, based on the tender requirement information of the tender topic, identifies the requirement type of each tender requirement topic and the requirement content of each tender requirement topic. The requirement type includes, but is not limited to, project task requirement type, project work requirement type, enterprise qualification requirement type and the like. The terminal identifies the title identification information of each tender requirement topic, and queries the requirement type that has a corresponding relationship with the title identification information in the requirement database as the requirement type of the tender requirement topic. The requirement database stores the topic identification range corresponding to each requirement type. That is, one requirement type can correspond to one or more tender requirement topics, and each tender requirement topic can correspond to one or more requirement types.

[0040] Then, the terminal identifies the location information corresponding to each requirement type of the tender announcement template, and fills the tender requirement title of each requirement type and the requirement content of the tender requirement title of each requirement type into the tender announcement template to obtain the tender requirement information of the tender subject.

[0041] The terminal uses the text recognition network in the large language model based on natural language processing technology to identify the qualification requirement information in the requirements of the bidding requirements of the enterprise qualification requirement type, and selects the enterprises corresponding to the enterprise qualification information that are adapted to each qualification requirement information in the Internet database or the cooperative enterprise database as the adapted enterprises for the bidding theme. Among them, the qualification requirement information includes, for example, the years of the enterprise, the scale of the enterprise, the registration cost of the enterprise, the scope of business, the number of personnel related to the enterprise and the project, the qualification information of the personnel related to the enterprise and the project, and other demand information. As long as there is an enterprise that meets the qualification requirement information, it is the adapted enterprise for the bidding theme.

[0042] Based on the above scheme, by splitting the demand content of each bidding demand topic of the bidding demand information, the bidding announcement information of each bidding theme is generated through template generation, which improves the comprehensiveness and accuracy of generating each bidding announcement information. Then, through the qualification adaptation method, the enterprises that are compatible with the bidding theme are identified, which improves the bidding accuracy of the target enterprises required by the bidding enterprises.

[0043] Optionally, the tender announcement information of each bidding topic is sent to each adapted enterprise and each non-adapted enterprise through the preset tender transmission channels of each adapted enterprise and the preset tender transmission channels of each non-adapted enterprise, including: for each bidding topic, calculating the enterprise adaptability between the enterprise qualification information of each adapted enterprise of the bidding topic and the qualification requirement information of the bidding topic through a adaptability algorithm, and dividing each adapted enterprise into enterprise groups of each adaptability level based on the enterprise adaptability of each adapted enterprise; identifying the tender transmission channels of each adaptability level and the tender transmission channels without adaptability level in the sending database, and sending the tender announcement information of the tender topic to the enterprise group of each adaptability level of the tender topic through the tender transmission channels of each adaptability level; sending the tender announcement information of the tender topic to the tender transmission channels of each non-adapted enterprise through the tender transmission channels without adaptability level.

[0044] In this embodiment, the terminal calculates the enterprise suitability between the enterprise qualification information of each adapted enterprise of the tender theme and the qualification requirement information of the tender theme through a suitability algorithm for each tender theme. The suitability algorithm is a ratio algorithm. The specific calculation process is that the terminal calculates the ratio between the number of qualification requirement information that meets the tender theme and the number of all qualification requirement information of the tender theme in the enterprise qualification information of each adapted enterprise, and obtains the enterprise suitability between each adapted enterprise and the tender theme.

[0045] Then, the terminal presets the adaptation levels corresponding to different enterprise adaptability ranges, and divides each adapted enterprise into enterprise groups of each adaptation level based on the enterprise adaptability of each adapted enterprise. The adaptation level includes a low adaptation level, a medium adaptation level, and a high adaptation level. Among them, the enterprise adaptability range corresponding to the low adaptation level is (1~30%), the enterprise adaptability range corresponding to the medium adaptation level is (30~60%), and the enterprise adaptability range corresponding to the high adaptation level is (60~100%). In the sending database, the bidding transmission channels of each adaptation level and the bidding transmission channels without adaptation level are identified, and the bidding announcement information of the bidding subject is sent to the enterprise group of each adaptation level of the bidding subject through the bidding transmission channels of each adaptation level. Finally, the terminal sends the bidding announcement information of the bidding subject to the bidding transmission channels of each non-adaptive enterprise through the bidding transmission channels without adaptation level. Among them, the sending database includes the corresponding relationship between each adaptation level and the bidding transmission channel. Among them, the bidding transmission channel without adaptation level is the public announcement channel, the bidding transmission channels corresponding to the low adaptation level are the email channel, the public announcement channel, and the telephone channel, the bidding transmission channels corresponding to the intermediate adaptation level are the telephone channel, the email channel, the public announcement channel, and the SMS channel, and the bidding transmission channels corresponding to the advanced adaptation level are the telephone channel, the email channel, the public announcement channel, the on-site channel of the personnel, the SMS channel, and the Internet information channel.

[0046] Based on the above scheme, the enterprises are classified into different levels by calculating their adaptability, so as to configure different bidding transmission channels, which effectively saves the bidding transmission cost and improves the accuracy of bidding transmission.

[0047] Optionally, based on the bidding information of each enterprise of the bidding theme and the bidding condition information of the bidding theme, the bidding information of each intended enterprise is screened from the bidding information of each enterprise, including: splitting the bidding condition information of the bidding theme into condition content of each bidding condition type, and identifying the bidding category corresponding to each bidding condition type in the bidding database; for each enterprise bidding information, splitting the enterprise bidding information into bidding content of each bidding category, and identifying the matching degree between the condition content of each bidding condition type and the bidding content of the bidding category corresponding to each bidding condition type through a semantic recognition network; when there is no matching degree below the matching degree threshold, taking the enterprise bidding information as the bidding information of the intended enterprise of the bidding theme.

[0048] In this embodiment, the terminal splits the bidding condition information of the bidding subject into the condition contents of each bidding condition type, and identifies the bidding category corresponding to each bidding condition type in the bidding database. The bidding category is each category included in the bidding document template attached to the bidding announcement information of each bidding subject. For each enterprise bidding information, the terminal splits the enterprise bidding information into the bidding content of each bidding category, and identifies the matching degree between the condition content of each bidding condition type and the bidding content of the bidding category corresponding to each bidding condition type through the semantic recognition network. The semantic recognition network is a text semantic recognition network (Convolutional Recurrent Neural Network, CRNN). The terminal identifies the condition semantics of each condition content and the bidding semantics of the bidding content through the semantic recognition network. Then, the terminal extracts the condition semantic feature vector of each condition semantic and the bidding semantic feature vector of the bidding semantic. Then, the similarity between the condition semantic feature vector of each condition semantic and the bidding semantic feature vector of the bidding semantic is calculated through the cosine similarity algorithm, and the matching degree between the condition content of each bidding condition type and the bidding content of the bidding category corresponding to each bidding condition type is obtained. Afterwards, the terminal determines whether there is a matching degree lower than a matching degree threshold preset in the terminal. When there is a matching degree lower than the matching degree threshold, the terminal directly regards the enterprise bidding information as the non-intended enterprise bidding information. When there is no matching degree lower than the matching degree threshold, the terminal regards the enterprise bidding information as the intended enterprise bidding information of the bidding subject.

[0049] Based on the above scheme, by splitting each bidding category and calculating the matching degree between the condition content of each bidding condition type and the bidding content of the bidding category corresponding to each bidding condition type, the bidding information of potential enterprises is screened, thereby improving the accuracy of screening the bidding information of potential enterprises.

[0050] Optionally, objective scoring is performed on the bidding information of each intended enterprise through a bidding evaluation network to obtain an objective scoring value for the bidding information of each intended enterprise, including: for each intended enterprise's bidding information, in the bidding category of the intended enterprise's bidding information, objective bidding content of objective bidding categories of objective types are screened, and based on the objective type of each objective bidding category, objective scoring indicators corresponding to each objective type are queried in the indicator database; objective bidding content of objective bidding categories of each objective type and objective scoring indicators corresponding to each objective type are input into the bidding evaluation network to identify sub-scores of objective bidding categories of each objective type; based on the sub-scores of objective bidding categories of each objective type and the weight values ​​of objective bidding categories of each objective type, objective scoring values ​​of the bidding information of the intended enterprises are determined.

[0051] In this embodiment, the terminal screens the objective bidding content of the objective bidding category of the objective type in the bidding category of the bidding information of each intended enterprise for the bidding information. Among them, in each category in the bidding document template of the bidding announcement information attached to each bidding theme, category identification information is included. Among them, the category identification information is an identification mark that identifies whether the category is an objective type or a subjective type. The identification mark can be identification information such as a text mark, a symbol mark, a color mark, and a letter mark. Among them, the objective type is an audit type with hard indicators in each category.

[0052] Based on the objective type of each objective bidding category, the terminal queries the objective scoring indicators corresponding to each objective type in the indicator database. Among them, the objective scoring indicators corresponding to each objective type include the content scope of the objective bidding content corresponding to each indicator scoring value. For example, if the objective bidding content is the business scope, each indicator scoring value corresponds to a business scope. The terminal identifies the business scope corresponding to the indicator scoring value to which the business scope of the objective bidding content belongs, thereby determining the objective scoring indicators of the objective bidding content.

[0053] Then, the terminal inputs the objective bidding content of each objective bidding category and the objective scoring index corresponding to each objective type into the bidding evaluation network to identify the sub-score value of each objective bidding category. The bidding evaluation network includes but is not limited to a classifier based on a reinforcement learning neural network.

[0054] Finally, the terminal determines the objective score value of the bidding information of the intended enterprise based on the sub-score value of the objective bidding category of each objective type and the weight value of the objective bidding category of each objective type. The weight value of the objective bidding category of each objective type is preset in the terminal. The determination method is that the terminal performs weighted summation processing on the sub-score value of the objective bidding category of each objective type through the weight value of the objective bidding category of each objective type to obtain the objective score value of the bidding information of the intended enterprise.

[0055] Based on the above scheme, the objective scoring values ​​of the objective bidding categories are weighted and summed to obtain the objective scoring values ​​of the bidding information of the intended enterprises, thereby improving the accuracy and practicality of the objective scoring values ​​of the bidding information of the intended enterprises.

[0056] Optionally, based on the expert review opinions of the bidding information of each intended enterprise, a subjective score value of the bidding information of each intended enterprise is generated, including: for each intended enterprise bidding information, splitting the expert review opinions of the bidding information of the intended enterprise into sub-expert review contents of the subjective bidding category of each subjective type, and identifying the review semantic information of each sub-expert review content through a semantic recognition network; querying the subjective scoring index of each subjective type in the index database, and identifying the indicator semantic information corresponding to each indicator value of each subjective scoring index through a semantic recognition network; for each subjective type, based on the review semantic information of the sub-expert review contents of the subjective bidding category of the subjective type and the indicator semantic information corresponding to each indicator value in the subjective scoring index of the subjective type, calculating the similarity between the sub-expert review contents and each indicator value through a semantic similarity algorithm, and selecting the indicator value corresponding to the maximum similarity as the target indicator value of the sub-expert review content; based on the target indicator value of the sub-expert review contents of the subjective bidding category of each subjective type and the weight value of the subjective bidding category of each subjective type, determining the subjective score value of the bidding information of the intended enterprise.

[0057] In this embodiment, for each intended enterprise bidding information, the terminal splits the expert review opinions of the intended enterprise bidding information into sub-expert review contents of subjective bidding categories of each subjective type, and identifies the review semantic information of each sub-expert review content through the semantic recognition network. Among them, each sub-expert review content is the evaluation content obtained by the expert review team for subjective evaluation of the bidding content of the subjective bidding category. The subjective type is a non-rigid indicator and an audit type with a relatively wide indicator range.

[0058] In the indicator database, the terminal queries the subjective scoring indicator of each subjective type, and identifies the indicator semantic information corresponding to each indicator value of each subjective scoring indicator through the semantic recognition network. Among them, the semantic recognition network here and the semantic recognition network below are the same as the semantic recognition network described above, and no redundant description is given here.

[0059] For each subjective type, the terminal calculates the similarity between the sub-expert review content and each indicator value through a semantic similarity algorithm based on the review semantic information of the sub-expert review content of the subjective bidding category of the subjective type and the indicator semantic information corresponding to each indicator value in the subjective scoring indicator of the subjective type. The semantic similarity algorithm may be an algorithm that extracts the semantic vector of each semantic information and then calculates the similarity based on the cosine similarity algorithm.

[0060] The terminal selects the index value corresponding to the maximum similarity as the target index value of the sub-expert review content. Finally, the terminal determines the subjective score value of the intended enterprise's bidding information based on the target index value of the sub-expert review content of each subjective type of subjective bidding category and the weight value of each subjective type of subjective bidding category. Specifically, the weight value of each subjective type of subjective bidding category is preset in the terminal. The determination method is that the terminal performs weighted summation processing on the target index value of the sub-expert review content of each subjective type of subjective bidding category through the weight value of each subjective type of subjective bidding category, and obtains the objective score value of the intended enterprise's bidding information.

[0061] Based on the above scheme, the subjective scoring values ​​of the subjective bidding categories are weighted and summed to obtain the subjective scoring values ​​of the bidding information of the intended enterprises, thereby improving the accuracy and practicality of the subjective scoring values ​​of the bidding information of the intended enterprises.

[0062] Optionally, based on the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise, the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme are screened as the target purchasing enterprises of the bidding theme, including: based on the adaptation level of the enterprise corresponding to the bidding information of each intended enterprise, the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise are weighted and processed to obtain the adapted objective scoring value of each intended enterprise bidding information and the adapted subjective scoring value of each intended enterprise bidding information; based on a preset first weight value of the objective scoring value and a preset second weight value of the subjective scoring value, the adapted objective scoring value of each intended enterprise bidding information and the adapted subjective scoring value of each intended enterprise bidding information are weighted and summed to obtain the target scoring value of each intended enterprise bidding information; the enterprises corresponding to the bidding information of each intended enterprise are sorted in order of the target scoring value from high to low to obtain an enterprise sequence, and the number of purchasing enterprises of the bidding theme is collected; and the enterprises with the number of purchasing enterprises of the bidding theme are screened in order of the enterprise sequence from front to back as the target purchasing enterprises of the bidding theme.

[0063] In this embodiment, the terminal performs weight adjustment processing on the objective score value of each intended enterprise bidding information and the subjective score value of each intended enterprise bidding information based on the adaptation level of the enterprise corresponding to each intended enterprise bidding information, and obtains the adapted objective score value of each intended enterprise bidding information and the adapted subjective score value of each intended enterprise bidding information. Among them, the terminal presets the score addition value corresponding to each adaptation level, and then, based on the adaptation level of the enterprise corresponding to each intended enterprise bidding information, the terminal adds the score addition value corresponding to each adaptation level to the objective score value of each intended enterprise bidding information and the subjective score value of each intended enterprise bidding information, and finally obtains the adapted objective score value of each intended enterprise bidding information and the adapted subjective score value of each intended enterprise bidding information. The obtained score values ​​comprehensively consider the influence of each adaptation level. The practicality and accuracy of the identified score values ​​are improved.

[0064] Then, based on the preset first weight value of the objective score value and the preset second weight value of the subjective score value, the terminal performs weighted summation processing on the adapted objective score value of each intended enterprise's bidding information and the adapted subjective score value of each intended enterprise's bidding information, respectively, to obtain the target score value of each intended enterprise's bidding information. After that, the terminal sorts the enterprises corresponding to the bidding information of each intended enterprise in order of the target score value from high to low, obtains the enterprise sequence, and collects the number of purchasing enterprises of the bidding theme. Among them, the number of purchasing enterprises of each bidding theme is preset in the terminal. Finally, the terminal selects the enterprises with the number of purchasing enterprises of the bidding theme in the order of the enterprise sequence from front to back as the target purchasing enterprises of the bidding theme.

[0065] Based on the above scheme, the score value is adjusted according to the adaptation level of each enterprise, which improves the practicality and accuracy of the score value. Then, the enterprises are screened in order from high to low according to the score value, which improves the accuracy of the screening.

[0066] This application also provides a bidding and procurement management example, such as Figure 2 As shown, the specific processing process includes the following steps: Step S201, obtaining the bidding requirement information of each bidding subject and the bidding condition information of each bidding subject.

[0067] Step S202, obtaining a tender notice template, and for each tender subject, identifying the requirement type and requirement content of each tender requirement topic based on the tender requirement information of the tender subject.

[0068] Step S203, identifying the location information corresponding to each requirement type of the tender announcement template, and filling the tender requirement title of each requirement type and the requirement content of the tender requirement title of each requirement type into the tender announcement template to obtain the tender requirement information of the tender subject.

[0069] Step S204, identifying each qualification requirement information in the requirement content of the bidding requirement topic of the enterprise qualification requirement type through a text recognition network, and selecting enterprises corresponding to the enterprise qualification information that are adapted to each qualification requirement information in an Internet database or a cooperative enterprise database as adapted enterprises for the bidding subject.

[0070] Step S205, for each bidding theme, calculate the enterprise suitability between the enterprise qualification information of each adapted enterprise of the bidding theme and the qualification requirement information of the bidding theme through the adaptability algorithm, and divide each adapted enterprise into enterprise groups of each adaptability level based on the enterprise suitability of each adapted enterprise.

[0071] Step S206, in the sending database, identifying the bidding transmission channels of each adaptation level and the bidding transmission channels without adaptation level, and sending the bidding announcement information of the bidding subject to the enterprise group of each adaptation level of the bidding subject through the bidding transmission channels of each adaptation level.

[0072] Step S207, sending the bidding announcement information of the bidding subject to the bidding transmission channels of each non-adaptive enterprise through the bidding transmission channel without adaptation level.

[0073] Step S208, collecting the enterprise bidding information of each enterprise for each bidding theme.

[0074] Step S209, splitting the bidding condition information of the bidding subject into condition contents of each bidding condition type, and identifying the bidding category corresponding to each bidding condition type in the bidding database.

[0075] Step S210, for each enterprise bidding information, split the enterprise bidding information into bidding contents of each bidding category, and identify the matching degree between the condition content of each bidding condition type and the bidding content of the bidding category corresponding to each bidding condition type through the semantic recognition network.

[0076] Step S211, when there is no matching degree lower than the matching degree threshold, the enterprise bidding information is used as the intended enterprise bidding information of the bidding subject.

[0077] Step S212, for each intended enterprise bidding information, in the bidding category of the intended enterprise bidding information, the objective bidding content of the objective bidding category of the objective type is screened, and based on the objective type of each objective bidding category, the objective scoring index corresponding to each objective type is queried in the index database.

[0078] Step S213, inputting the objective bidding contents of each objective bidding category and the objective scoring indicators corresponding to each objective type into the bidding evaluation network, and identifying the sub-score values ​​of each objective bidding category.

[0079] Step S214, determining the objective scoring value of the bidding information of the intended enterprise based on the sub-score value of the objective bidding category of each objective type and the weight value of the objective bidding category of each objective type.

[0080] Step S215, for each potential enterprise bidding information, split the expert review opinions of the potential enterprise bidding information into sub-expert review contents of each subjective bidding category, and identify the review semantic information of each sub-expert review content through the semantic recognition network.

[0081] Step S216: query the subjective scoring index of each subjective type in the index database, and identify the index semantic information corresponding to each index value of each subjective scoring index through the semantic recognition network.

[0082] Step S217, for each subjective type, based on the review semantic information of the sub-expert review content of the subjective bidding category of the subjective type, and the indicator semantic information corresponding to each indicator value in the subjective scoring indicator of the subjective type, the similarity between the sub-expert review content and each indicator value is calculated through a semantic similarity algorithm, and the indicator value corresponding to the maximum similarity is selected as the target indicator value of the sub-expert review content.

[0083] Step S218, determining the subjective scoring value of the bidding information of the intended enterprise based on the target index value of the sub-expert review content of each subjective bidding category and the weight value of each subjective bidding category.

[0084] Step S219, based on the adaptation level of the enterprise corresponding to the bidding information of each intended enterprise, the objective score value of each intended enterprise's bidding information and the subjective score value of each intended enterprise's bidding information are weighted and adjusted to obtain the adapted objective score value of each intended enterprise's bidding information and the adapted subjective score value of each intended enterprise's bidding information.

[0085] Step S220, based on the first weight value of the preset objective score value and the second weight value of the preset subjective score value, the adapted objective score value of each intended enterprise's bidding information and the adapted subjective score value of each intended enterprise's bidding information are weighted and summed up to obtain the target score value of each intended enterprise's bidding information.

[0086] Step S221, sorting the enterprises corresponding to the bidding information of each intended enterprise in descending order of target score values, obtaining an enterprise sequence, and collecting the number of purchasing enterprises of the bidding subject.

[0087] Step S222, in the order of the enterprise sequence from front to back, select enterprises with the same number of purchasing enterprises as the target purchasing enterprises of the bidding subject.

[0088] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0089] Based on the same inventive concept, the embodiment of the present application also provides a bidding procurement management device for implementing the bidding procurement management method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more bidding procurement management device embodiments provided below can refer to the limitations of the bidding procurement management method above, and will not be repeated here.

[0090] In an exemplary embodiment, Figure 3 As shown, a bidding procurement management device is provided, including: an acquisition module 310, a sending module 320, a scoring module 330, a generation module 340 and a screening module 350, wherein: The acquisition module 310 is used to acquire the bidding requirement information of each bidding theme and the bidding condition information of each bidding theme, and identify the bidding announcement information of each bidding theme and the matching enterprise of each bidding theme based on the bidding requirement information of each bidding theme; The sending module 320 is used to send the bidding announcement information of each bidding topic to each of the matching enterprises and each of the non-matching enterprises through the preset bidding transmission channels of each matching enterprise and the preset bidding transmission channels of each non-matching enterprise, and collect the enterprise bidding information of each enterprise for each bidding topic; Scoring module 330 is used for screening the bidding information of each intended enterprise from the bidding information of each enterprise based on the bidding information of each enterprise and the bidding condition information of the bidding theme for each bidding theme, and objectively scoring the bidding information of each intended enterprise through the bidding evaluation network to obtain the objective scoring value of the bidding information of each intended enterprise; A generating module 340 is used to receive expert review opinions on the bidding information of each of the intended enterprises, and generate a subjective score value for the bidding information of each of the intended enterprises based on the expert review opinions on the bidding information of each of the intended enterprises; The screening module 350 is used to screen the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme as the target purchasing enterprise of the bidding theme based on the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise.

[0091] Optionally, the acquisition module 310 is specifically configured to: Obtain a tender notice template, and for each tender subject, identify the requirement type of each tender requirement topic and the requirement content of each tender requirement topic based on the tender requirement information of the tender subject; Identify the location information corresponding to each requirement type of the tender announcement template, and fill the tender requirement title of each requirement type and the requirement content of the tender requirement title of each requirement type into the tender announcement template to obtain the tender requirement information of the tender subject; Through the text recognition network, the qualification requirement information in the requirement content of the bidding requirement topic of the enterprise qualification requirement type is identified, and the enterprises corresponding to the enterprise qualification information that are adapted to each of the qualification requirement information are screened in the Internet database or the cooperative enterprise database as the adapted enterprises of the bidding subject.

[0092] Optionally, the sending module 320 is specifically configured to: For each bidding theme, the enterprise qualification information of each suitable enterprise of the bidding theme and the enterprise fitness between the qualification requirement information of the bidding theme are calculated by using the fitness algorithm, and based on the enterprise fitness of each suitable enterprise, each suitable enterprise is divided into enterprise groups of each fitness level; In the sending database, identifying the bidding transmission channels of each adaptation level and the bidding transmission channels without adaptation level, and sending the bidding announcement information of the bidding subject to the enterprise group of each adaptation level of the bidding subject through the bidding transmission channels of each adaptation level; The bidding announcement information of the bidding subject is sent to the bidding transmission channels of each non-adaptable enterprise through the bidding transmission channel without adaptation level.

[0093] Optionally, the scoring module 330 is specifically used to: Splitting the bidding condition information of the bidding subject into condition contents of each bidding condition type, and identifying the bidding category corresponding to each bidding condition type in the bidding database; For each enterprise bidding information, the enterprise bidding information is split into bidding contents of each bidding category, and the matching degree between the condition content of each bidding condition type and the bidding contents of the bidding category corresponding to each bidding condition type is respectively identified through a semantic recognition network; When there is no matching degree lower than the matching degree threshold, the enterprise bidding information is used as the intended enterprise bidding information of the bidding subject.

[0094] Optionally, the scoring module 330 is specifically used to: For each intended enterprise bidding information, in the bidding category of the intended enterprise bidding information, the objective bidding content of the objective bidding category of the objective type is screened, and based on the objective type of each objective bidding category, the objective scoring index corresponding to each objective type is searched in the index database; Inputting the objective bidding contents of the objective bidding categories of each objective type and the objective scoring indicators corresponding to each objective type into the bidding evaluation network, and identifying the sub-score values ​​of the objective bidding categories of each objective type; Based on the sub-score values ​​of the objective bidding category of each objective type and the weight value of the objective bidding category of each objective type, the objective score value of the bidding information of the intended enterprise is determined.

[0095] Optionally, the generating module 340 is specifically configured to: For each intended enterprise bidding information, the expert review opinions of the intended enterprise bidding information are split into sub-expert review contents of subjective bidding categories of each subjective type, and the review semantic information of each sub-expert review content is identified through the semantic recognition network; In the indicator database, query the subjective scoring indicator of each subjective type, and identify the indicator semantic information corresponding to each indicator value of each subjective scoring indicator through the semantic recognition network; For each subjective type, based on the review semantic information of the sub-expert review content of the subjective bidding category of the subjective type and the indicator semantic information corresponding to each indicator value in the subjective scoring indicator of the subjective type, the similarity between the sub-expert review content and each indicator value is calculated through a semantic similarity algorithm, and the indicator value corresponding to the maximum similarity is selected as the target indicator value of the sub-expert review content; Based on the target index value of the sub-expert review content of each subjective bidding category of each subjective type and the weight value of each subjective bidding category of each subjective type, the subjective scoring value of the bidding information of the intended enterprise is determined.

[0096] Optionally, the screening module 350 is specifically used for: Based on the adaptation level of the enterprise corresponding to each of the intended enterprise bidding information, the objective score value of each intended enterprise bidding information and the subjective score value of each intended enterprise bidding information are weighted and adjusted to obtain the adaptation objective score value of each intended enterprise bidding information and the adaptation subjective score value of each intended enterprise bidding information; Based on a preset first weight value of the objective scoring value and a preset second weight value of the subjective scoring value, weighted sum processing is performed on the adapted objective scoring value of each intended enterprise bidding information and the adapted subjective scoring value of each intended enterprise bidding information to obtain a target scoring value of each intended enterprise bidding information; According to the target score from high to low, the enterprises corresponding to the bidding information of each intended enterprise are sorted to obtain an enterprise sequence, and the number of purchasing enterprises of the bidding subject is collected; According to the order of the enterprise sequence from front to back, enterprises with the same number of purchasing enterprises as the bidding subject are selected as the target purchasing enterprises of the bidding subject.

[0097] Each module in the above-mentioned bidding and procurement management device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0098] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a bidding and procurement management method is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0099] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0100] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0101] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0102] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0103] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0104] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0105] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for managing bidding and procurement, characterized in that: The method comprises: Acquire the bidding requirement information of each bidding theme and the bidding condition information of each bidding theme, and identify the bidding announcement information of each bidding theme and the matching enterprise of each bidding theme based on the bidding requirement information of each bidding theme; Through the preset bidding transmission channels of each adapted enterprise and the preset bidding transmission channels of each non-adapted enterprise, the bidding announcement information of each bidding topic is sent to each adapted enterprise and each non-adapted enterprise, and the enterprise bidding information of each enterprise for each bidding topic is collected; For each bidding theme, based on the bidding information of each enterprise of the bidding theme and the bidding condition information of the bidding theme, the bidding information of each intended enterprise is screened from the bidding information of each enterprise, and the bidding information of each intended enterprise is objectively scored through the bidding evaluation network to obtain the objective scoring value of the bidding information of each intended enterprise; receiving expert review opinions on the bidding information of each of the intended enterprises, and generating subjective scoring values ​​for the bidding information of each of the intended enterprises based on the expert review opinions on the bidding information of each of the intended enterprises; Based on the objective scoring values ​​of the bidding information of each of the intended enterprises and the subjective scoring values ​​of the bidding information of each of the intended enterprises, the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme are screened as the target purchasing enterprises of the bidding theme.

2. The method according to claim 1, characterized in that The step of identifying the tender announcement information of each tender theme and the suitable enterprises of each tender theme based on the tender demand information of each tender theme includes: Obtain a tender notice template, and for each tender subject, identify the requirement type of each tender requirement topic and the requirement content of each tender requirement topic based on the tender requirement information of the tender subject; Identify the location information corresponding to each requirement type of the tender announcement template, and fill the tender requirement title of each requirement type and the requirement content of the tender requirement title of each requirement type into the tender announcement template to obtain the tender requirement information of the tender subject; Through the text recognition network, the qualification requirement information in the requirement content of the bidding requirement topic of the enterprise qualification requirement type is identified, and the enterprises corresponding to the enterprise qualification information that are adapted to each of the qualification requirement information are screened in the Internet database or the cooperative enterprise database as the adapted enterprises of the bidding subject.

3. The method according to claim 2, characterized in that The step of sending the bidding announcement information of each bidding topic to each of the adaptable enterprises and each of the non-adaptable enterprises through the preset bidding transmission channels of each of the adaptable enterprises and the preset bidding transmission channels of each of the non-adaptable enterprises includes: For each bidding theme, the enterprise qualification information of each suitable enterprise of the bidding theme and the enterprise fitness between the qualification requirement information of the bidding theme are calculated by using the fitness algorithm, and based on the enterprise fitness of each suitable enterprise, each suitable enterprise is divided into enterprise groups of each fitness level; In the sending database, identifying the bidding transmission channels of each adaptation level and the bidding transmission channels without adaptation level, and sending the bidding announcement information of the bidding subject to the enterprise group of each adaptation level of the bidding subject through the bidding transmission channels of each adaptation level; The bidding announcement information of the bidding subject is sent to the bidding transmission channels of each non-adaptable enterprise through the bidding transmission channel without adaptation level.

4. The method according to claim 1, characterized in that: The step of screening the bidding information of each intended enterprise from the bidding information of each enterprise based on the bidding information of each enterprise and the bidding condition information of the bidding subject includes: Splitting the bidding condition information of the bidding subject into condition contents of each bidding condition type, and identifying the bidding category corresponding to each bidding condition type in the bidding database; For each enterprise bidding information, the enterprise bidding information is split into bidding contents of each bidding category, and the matching degree between the condition content of each bidding condition type and the bidding contents of the bidding category corresponding to each bidding condition type is respectively identified through a semantic recognition network; When there is no matching degree lower than the matching degree threshold, the enterprise bidding information is used as the intended enterprise bidding information of the bidding subject.

5. The method according to claim 4, characterized in that The bidding evaluation network objectively scores the bidding information of each intended enterprise to obtain an objective score value of the bidding information of each intended enterprise, including: For each intended enterprise bidding information, in the bidding category of the intended enterprise bidding information, the objective bidding content of the objective bidding category of the objective type is screened, and based on the objective type of each objective bidding category, the objective scoring index corresponding to each objective type is searched in the index database; Inputting the objective bidding contents of the objective bidding categories of each objective type and the objective scoring indicators corresponding to each objective type into the bidding evaluation network, and identifying the sub-score values ​​of the objective bidding categories of each objective type; Based on the sub-score values ​​of the objective bidding category of each objective type and the weight value of the objective bidding category of each objective type, the objective score value of the bidding information of the intended enterprise is determined.

6. The method according to claim 5, characterized in that The subjective scoring value of the bidding information of each intended enterprise is generated based on the expert review opinions of the bidding information of each intended enterprise, including: For each intended enterprise bidding information, the expert review opinions of the intended enterprise bidding information are split into sub-expert review contents of subjective bidding categories of each subjective type, and the review semantic information of each sub-expert review content is identified through the semantic recognition network; In the indicator database, query the subjective scoring indicator of each subjective type, and identify the indicator semantic information corresponding to each indicator value of each subjective scoring indicator through the semantic recognition network; For each subjective type, based on the review semantic information of the sub-expert review content of the subjective bidding category of the subjective type and the indicator semantic information corresponding to each indicator value in the subjective scoring indicator of the subjective type, the similarity between the sub-expert review content and each indicator value is calculated through a semantic similarity algorithm, and the indicator value corresponding to the maximum similarity is selected as the target indicator value of the sub-expert review content; Based on the target index value of the sub-expert review content of each subjective bidding category of each subjective type and the weight value of each subjective bidding category of each subjective type, the subjective scoring value of the bidding information of the intended enterprise is determined.

7. The method according to claim 3, characterized in that The step of selecting the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme as the target purchasing enterprise of the bidding theme based on the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise includes: Based on the adaptation level of the enterprise corresponding to each of the intended enterprise bidding information, the objective score value of each intended enterprise bidding information and the subjective score value of each intended enterprise bidding information are weighted and adjusted to obtain the adaptation objective score value of each intended enterprise bidding information and the adaptation subjective score value of each intended enterprise bidding information; Based on a preset first weight value of the objective scoring value and a preset second weight value of the subjective scoring value, weighted sum processing is performed on the adapted objective scoring value of each intended enterprise bidding information and the adapted subjective scoring value of each intended enterprise bidding information to obtain a target scoring value of each intended enterprise bidding information; According to the target score from high to low, the enterprises corresponding to the bidding information of each intended enterprise are sorted to obtain an enterprise sequence, and the number of purchasing enterprises of the bidding subject is collected; According to the order of the enterprise sequence from front to back, enterprises with the same number of purchasing enterprises as the bidding subject are selected as the target purchasing enterprises of the bidding subject.

8. A bidding and procurement management device, characterized in that: The device comprises: An acquisition module, used to acquire the tender demand information of each tender theme and the tender condition information of each tender theme, and identify the tender announcement information of each tender theme and the adaptable enterprise of each tender theme based on the tender demand information of each tender theme; A sending module, used to send the bidding announcement information of each bidding topic to each of the adapted enterprises and each of the non-adapted enterprises through the preset bidding transmission channels of each adapted enterprise and the preset bidding transmission channels of each non-adapted enterprise, and collect the enterprise bidding information of each enterprise for each bidding topic; The scoring module is used to screen the bidding information of each intended enterprise from the bidding information of each enterprise based on the bidding information of each enterprise and the bidding condition information of the bidding theme for each bidding theme, and objectively score the bidding information of each intended enterprise through the bidding evaluation network to obtain the objective score value of the bidding information of each intended enterprise; A generating module, used for receiving the expert review opinions of the bidding information of each of the intended enterprises, and generating a subjective score value of the bidding information of each of the intended enterprises based on the expert review opinions of the bidding information of each of the intended enterprises; The screening module is used to screen the enterprises corresponding to the bidding information of each target intended enterprise corresponding to the bidding theme as the target purchasing enterprise of the bidding theme based on the objective scoring value of the bidding information of each intended enterprise and the subjective scoring value of the bidding information of each intended enterprise.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images