Bidding subjective item review method and device, related equipment and program product

Abstract

The invention discloses a bidding subjective item review method and device, related equipment and a program product, an AI expert database is constructed in advance, each AI expert is obtained by training a large model through different fields and professional data, and infinite extension and flexible configuration of expert resources are realized. And each review element and scoring rule after refining the subjective review item are further obtained, so that the objectivity and accuracy of review of the subjective review item are improved. And the user selects target AI experts from the AI expert database, and sets attention weights for different review elements for each target AI expert so as to adapt to different review requirements. And calling the target AI expert to be combined with a scoring rule of the review elements to generate scores of the bidding file in the review elements, and performing weighted summation according to attention weights to obtain a scoring result. According to the method, the evaluation efficiency and objectivity can be improved, the user is supported to select different AI experts and flexibly configure attention weights, and evaluation of subjective items is more scientific and reasonable.

Description

[0001] This application claims the priority of a domestic application filed with the China Patent Office on January 8, 2025, with application number 202510025495.1 and invention name “Method, device, related equipment and program product for subjective item evaluation in bidding and tendering”, all contents of which are incorporated by reference in this application. Technical Field

[0002] The present application relates to the field of natural language processing technology, and more specifically, to a method, device, related equipment and program product for evaluating subjective items in bidding. Background Art

[0003] In the current bidding and tendering review system, human experts are usually relied on for review. The review criteria involve the review of subjective items. The traditional method is based on the subjective judgment of human experts. This review method has the following problems:

[0004] (1) Expert resources are limited and it is difficult to cope with large-scale review needs.

[0005] (2) Manual review is easily influenced by personal subjective preferences, which may damage the fairness of the review results.

[0006] (3) The review process is cumbersome and time-consuming, which affects the review efficiency.

[0007] In view of this, some fields have attempted to introduce AI review systems, but current AI review systems mostly rely on a single model or predefined scoring rules, lack flexibility, and have difficulty fully reflecting the true value of the review object, especially in the lack of scientific and reasonable implementation plans for the review of subjective items. Summary of the invention

[0008] In view of the above problems, in order to at least solve some or all of the problems existing in the traditional solution, this application is proposed to provide a bidding subjective item evaluation method, device, related equipment and program product. The specific solution is as follows:

[0009] In the first aspect, a method for evaluating subjective items in bidding is provided, including:

[0010] Obtain the bidding documents of the current bidder, as well as the evaluation elements corresponding to the subjective evaluation items and the scoring rules of the evaluation elements;

[0011] In response to the user's instruction to select an AI expert, determine the target AI expert selected by the user from a configured AI expert database, where different AI experts in the AI ​​expert database are large models trained using professional data in different fields;

[0012] In response to the user setting the attention weight of each target AI expert to each review element, the attention weight of each target AI expert to each review element is obtained;

[0013] Calling each of the target AI experts to instruct the target AI experts to generate a score for the bid document in the evaluation element in combination with the scoring rule of each of the evaluation elements;

[0014] The scores of each of the evaluation factors generated by each of the target AI experts are weighted and summed according to the attention weight to obtain the individual basic score of the current bidder in the subjective evaluation item, and the score of the current bidder by each of the target AI experts in the subjective evaluation item is determined at least based on the individual basic score.

[0015] In a possible design, in another implementation of the first aspect of the embodiment of the present application, the process of determining the score of the current bidder in the subjective review item by each target AI expert based at least on the single basic score includes:

[0016] Obtaining the basic score of each bidder in the subjective evaluation item, and grading all bidders according to the basic score;

[0017] According to the total value of the configured horizontal comparison score, determine the horizontal comparison score corresponding to each level, and obtain the horizontal comparison score corresponding to the level of the current bidder;

[0018] The individual basic score of the current bidder in the subjective evaluation item and the horizontal comparison score of the current bidder are added together to obtain the score of the current bidder in the subjective evaluation item.

[0019] In a possible design, in another implementation of the first aspect of the embodiment of the present application, the method further includes:

[0020] Calling each of the target AI experts to instruct the target AI experts to summarize the innovative evaluation factors with feasibility and rationality for the bid documents of the current bidder and the bid documents of other bidders, in addition to the evaluation factors corresponding to the subjective evaluation items, to obtain the innovative evaluation factors corresponding to each bidder generated by the target AI experts;

[0021] Determine the divergent innovation score of each bidder according to the number of innovation evaluation elements of each bidder;

[0022] The individual basic score of the current bidder in the subjective evaluation item, the horizontal comparison score of the current bidder and the divergent innovation score of the current bidder are added together to obtain the score of the current bidder in the subjective evaluation item.

[0023] In a possible design, in another implementation of the first aspect of the embodiment of the present application, the process of determining the divergent innovation score of each bidder according to the number of innovation evaluation elements of each bidder includes:

[0024] All bidders are classified according to the number of innovation evaluation elements mentioned;

[0025] According to the total value of the configured divergent innovation points, the divergent innovation points corresponding to each level are determined, and the divergent innovation points corresponding to the level of each bidder are obtained.

[0026] In a possible design, in another implementation of the first aspect of the embodiment of the present application, before obtaining each review factor corresponding to the subjective review item and the scoring rule of the review factor, it also includes:

[0027] Determine the subjective evaluation items based on the bid evaluation method in the bidding documents;

[0028] The big model is called to instruct the big model to subdivide the subjective evaluation items according to the evaluation method in the bidding document to obtain the subdivided evaluation elements and corresponding scoring rules.

[0029] In a possible design, in another implementation of the first aspect of the embodiment of the present application, calling the target AI expert to instruct the target AI expert to generate a score for the bid document in the evaluation element in combination with the scoring rule for each evaluation element includes:

[0030] Obtain a prompt format template of a prompt instruction, wherein the prompt format template includes a task instruction, a bid document slot, an evaluation factor slot, and a scoring rule slot, wherein the task instruction is used to instruct the large model to find corresponding content from the bid document in the bid document slot according to the evaluation factor in the evaluation factor slot, and to score based on the scoring rule in the scoring rule slot;

[0031] Fill the bid document of the current bidder into the bid document slot, fill the evaluation factors into the evaluation factor slot, fill the scoring rules corresponding to the evaluation factors into the scoring rule slot, obtain a first prompt instruction prompt, input the first prompt instruction prompt to the target AI expert, and obtain the score of the bid document generated by the target AI expert for the evaluation factors.

[0032] In one possible design, in another implementation of the first aspect of the embodiments of the present application, the task instruction is also used to instruct the large model to generate scoring reasons.

[0033] In a second aspect, a bidding subjective item evaluation device is provided, comprising:

[0034] A data acquisition unit, used to acquire the bidding documents of the current bidder, and to acquire the evaluation elements corresponding to the subjective evaluation items, and the scoring rules of the evaluation elements;

[0035] An AI expert selection unit, configured to respond to an instruction from a user to select an AI expert and determine a target AI expert selected by the user from a configured AI expert database, wherein different AI experts in the AI ​​expert database are large models trained using professional data from different fields;

[0036] A weight setting unit, configured to obtain the attention weight of each target AI expert to each review element in response to the user setting the attention weight of each review element for each target AI expert;

[0037] An AI expert scoring unit, configured to call each of the target AI experts to instruct the target AI experts to generate a score for the bid document in the evaluation element in combination with a scoring rule for each of the evaluation elements;

[0038] A single basic score calculation unit, used to perform weighted summation of the scores of each of the evaluation elements generated by each of the target AI experts according to the attention weight, to obtain the single basic score of the current bidder in the subjective evaluation item;

[0039] The total score determination unit is used to determine the score of each target AI expert for the current bidder in the subjective review item based at least on the single basic score.

[0040] In a third aspect, an electronic device is provided, comprising: a memory and a processor;

[0041] The memory is used to store programs;

[0042] The processor is used to execute the program to implement the various steps of the bidding and tendering subjective item evaluation method described in any one of the first aspects of the present application.

[0043] In a fourth aspect, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the various steps of the bidding and tendering subjective item evaluation method described in any one of the aforementioned first aspects of the present application are implemented.

[0044] In a fifth aspect, a computer program product is provided, including a computer program, which, when executed by a processor, implements the various steps of the bidding and tendering subjective item evaluation method described in any one of the aforementioned first aspects of the present application.

[0045] Through the above technical solution, this application pre-builds an AI expert database, which includes several different AI experts (virtual experts). Each AI expert is obtained by training a large model through data from different fields and professions, so that unlimited expansion and flexible configuration of expert resources can be achieved. For the subjective review items to be reviewed, this application can obtain the refined review elements and scoring rules for the subjective review items. The objectivity and accuracy of the review of the subjective review items are improved through the refined multi-dimensional review elements and scoring rules. Users can select the target AI experts required for this review from the AI ​​expert database according to the review requirements. In addition, in order to be closer to the real manual expert evaluation method and ensure the differences between different AI experts, this application also supports users to set the attention weights for different review elements for each target AI expert, that is, users can dynamically configure the attention weights of each target AI expert to adapt to different review needs. Then, by calling the target AI expert, instructing the target AI expert to combine the scoring rules of each evaluation factor, generate the score of the bid document in the evaluation factor, and weight the score of each evaluation factor according to the attention weight to obtain the single basic score of the current bidder in the subjective evaluation item, and based on this, determine the score of the current bidder in the subjective evaluation item by the target AI expert. The review method of this application can improve the efficiency and objectivity of the review, and supports users to select different AI experts and flexibly configure their attention weights, which is more scientific and reasonable in the review of subjective items. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0047] Figure 1 A schematic diagram of an implementation system architecture of a method for evaluating subjective items in bidding provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of a terminal structure provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a server structure provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of a process flow of a subjective item evaluation method for bidding provided in an embodiment of the present application;

[0051] Figure 5 A schematic diagram of a scenario for determining subjective evaluation items from a bidding document provided in an embodiment of the present application;

[0052] Figure 6 A schematic diagram of the structure of a bidding subjective item evaluation device provided in an embodiment of the present application;

[0053] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] This application provides a method for evaluating subjective items in bidding, which can be applied to Figure 1 The system architecture shown in FIG. 1 may include a terminal 100 and a server 200. The server 200 may include one or more servers ( Figure 1 A server is included as an example for explanation).

[0056] The terminal 100 or the server 200 can be used alone to execute the bidding subjective item evaluation method provided in the embodiment of the present application. In addition, the terminal 100 and the server 200 can also be used in collaboration to execute the bidding subjective item evaluation method provided in the embodiment of the present application.

[0057] Next describe Figure 1 The product form of the mid-terminal 100;

[0058] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a conference terminal, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any limitation on this.

[0059] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0060] refer to Figure 2As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160, a speaker 161, a microphone 162, an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 These are merely examples of terminals or multi-function devices and do not constitute limitations on the terminals or multi-function devices, which may include more or fewer components than those shown in the figures, or combinations of certain components, or different components.

[0061] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multi-function device. Specifically, the input unit 130 may include a touch screen 131 and / or other input devices 132. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute commands sent by the processor 170; the touch signal at least includes contact point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition to the touch screen 131, the input unit 130 may also include other input devices. Specifically, other input devices 132 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, etc.

[0062] The display unit 140 can be used to display information input by the user or information provided to the user, various menus of the terminal 100, interactive interfaces, file display and / or playback of any multimedia file. In the embodiment of the present application, the display unit 140 can be used to display various interactive interfaces, processing results, etc. in the bidding subjective item evaluation method.

[0063] The memory 120 may be used to store instructions and data.

[0064] Processor 170 is the control center of terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100, and executes various functions of terminal 100 and processes data by running or executing instructions stored in memory 120 and calling data stored in memory 120, thereby controlling the terminal device as a whole.

[0065] Among them, the memory 120 can be used to store software codes related to the bidding and tendering subjective item evaluation method, the processor 170 can execute the steps of the bidding and tendering subjective item evaluation method, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to realize corresponding functions.

[0066] The RF unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call. For example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. In an embodiment of the present application, the RF unit 110 can send data to the server 200 and receive the processing results sent by the server 200. Exemplarily, the RF unit 110 sends the received bidder's bid document to the server 200, and the server 200 performs a subjective review of the bid document, obtains the scores of each target AI expert, and returns the scores to the terminal 100.

[0067] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0068] Although not shown, the terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied in the following embodiments. Figure 2 In the terminal 100 shown.

[0069] Next describe Figure 1 The product form of the server 200;

[0070] Figure 3 A structural diagram of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0071] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0072] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0073] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0074] The memory 204 may be used to store software codes related to the subjective item evaluation method for bidding and tendering, the processor 202 may execute the steps of the subjective item evaluation method for bidding and tendering, and may also schedule other units to implement corresponding functions.

[0075] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0076] The present application embodiment provides a method for evaluating subjective items in bidding, and takes the method as an example of applying the method to a computer device, which can be specifically Figure 1 The terminal 100 or the system consisting of the terminal 100 and the server 200. Figure 4The subjective item evaluation method of bidding specifically includes the following steps:

[0077] Step S100: Obtain the bidding document of the current bidder, and obtain each evaluation factor corresponding to the subjective evaluation item, and the scoring rules of the evaluation factor.

[0078] Specifically, each bidder can submit a bid document for the bidding document. The bid document of each bidder needs to be reviewed, and the review process is carried out according to the review method specified in the bidding document, which specifies various review items. Some of these review items are objective review items, and some are subjective review items. This application mainly focuses on the review process of subjective review items.

[0079] In order to improve the objectivity and accuracy of the review of subjective review items, the present application may pre-subdivide the subjective review items into review elements of multiple dimensions and corresponding scoring rules for the review elements.

[0080] Let’s take the elevator bidding process as an example:

[0081] The bidding documents include a subjective review item: "Supply and installation plan". This subjective review item can be divided into several review elements, which can be further classified into: technical plan, installation and construction progress, quality assurance, personnel guarantee, installation and commissioning, acceptance and handover, etc. Taking the installation and construction progress as an example, it can include the following review elements: installation cycle and reasonableness of the construction period, packaging, marking, transportation and delivery details, etc. Among them, each review element corresponds to a scoring rule. Taking the installation cycle and reasonableness of the construction period as an example, the corresponding scoring rule can be:

[0082] {'Level 1': 'The installation period complies with the provisions of the bidding documents, is reasonable, synchronized with the civil engineering project, and does not affect the construction progress of other professional projects.', 'Level 2': 'The installation period basically complies with the provisions of the bidding documents, but there is a certain degree of conflict or unreasonableness.', 'Level 3': 'The installation period does not comply with the provisions of the bidding documents, is unreasonable, has serious conflicts or does not affect the construction progress of other professional projects.'}.

[0083] Step S110: In response to the user's instruction to select an AI expert, determine the target AI expert selected by the user from the configured AI expert database.

[0084] Among them, the AI ​​expert database is configured with several different AI experts, and different AI experts are large models trained with data from different fields and professions.

[0085] That is, this application can pre-collect and train large models from different fields and with different professional backgrounds to form an AI expert library (virtual experts). By configuring the AI ​​expert library, unlimited expansion and flexible configuration of expert resources can be achieved without being limited by the limitations of artificial expert resources.

[0086] In this embodiment, according to the needs of the bidding business, large models with different fields and professional background knowledge can be trained as AI experts, such as engineering and construction AI experts, household appliances AI experts, etc.

[0087] Users can select the target AI experts needed for this review from the AI ​​expert database according to the review requirements. The number of target AI experts can be one or more, which can be determined by the user. Users can select randomly or according to set conditions.

[0088] Step S120, in response to the user's operation of setting the attention weight of each target AI expert to each review element, the attention weight of each target AI expert to each review element is obtained.

[0089] Specifically, after the user selects the target AI expert, this embodiment further allows the user to set the attention weight for each target AI expert. Take expert 1 as an example: define the review elements corresponding to the subjective review items as review element 1-review element n. Then the attention weight of expert 1 for each review element is: W1-Wn.

[0090] Among them, the target AI expert's attention weight to each review factor can be understood as the target AI expert's tendency to score each review factor. Different attention weights indicate that the target AI expert pays different attention to different review factors, which is more in line with the review logic of real artificial experts. Different artificial experts pay different attention to different review factors. In this step, by allowing the user to set the attention weight of each review factor for the target AI expert, each target AI expert can be flexibly configured to adapt to different review needs.

[0091] Optionally, the sum of the attention weights of the same target AI expert to each review factor is 100%.

[0092] Step S130: call each target AI expert to instruct the target AI expert to generate a score for the bid document in the evaluation factor in combination with the scoring rules for each evaluation factor.

[0093] Specifically, each target AI expert is actually a large model. In this step, the large model corresponding to each target AI expert can be called to instruct the large model to score the current bidder's bid document in combination with the scoring rules of the evaluation elements, thereby obtaining the score of the current bidder on each evaluation element output by the large model. Still taking the evaluation elements including evaluation element 1-evaluation element n as an example, the scores of each evaluation element output by the target AI expert are X1-Xn respectively.

[0094] Step S140: perform weighted summation of the scores of each evaluation factor generated by each target AI expert according to the attention weight to obtain the individual basic score of the current bidder in the subjective evaluation item, and determine the score of each target AI expert on the current bidder in the subjective evaluation item at least based on the individual basic score.

[0095] Specifically, for each target AI expert, the scores of each evaluation factor generated by it can be weighted and summed according to the attention weights of the corresponding evaluation factors, and the result can be used as the individual basic score of the current bidder in the subjective evaluation item.

[0096] At least based on the single basic score, determine the score of each target AI expert on the current bidder in the subjective evaluation item.

[0097] For each bidder, the above process can be followed to obtain the score of the bidder in the subjective review item by each target AI expert.

[0098] The method provided in the embodiment of the present application realizes unlimited expansion and flexible configuration of expert resources by constructing an AI (virtual) expert database. Users can dynamically adjust the attention weight of the selected target AI experts to meet different review needs. The method of the present application subdivides the subjective review items into multi-dimensional review elements and scoring rules, and improves the objectivity and accuracy of the review by calling the target AI experts to score each review element.

[0099] In some embodiments of the present application, the following processing steps may be further added before obtaining the review elements and scoring rules corresponding to the subjective review items in the aforementioned step S100:

[0100] Determine the subjective evaluation items based on the bid evaluation method in the bidding documents.

[0101] The big model is called to instruct the big model to subdivide the subjective evaluation items according to the evaluation method in the bidding documents, and obtain the subdivided evaluation elements and corresponding scoring rules.

[0102] Combination Figure 5 , which takes the bidding documents for elevators as an example and illustrates an example of determining subjective evaluation items based on the bidding documents.

[0103] The appendix to the bid evaluation method can be extracted from the bidding documents. The appendix to the bid evaluation method is a key component of the bid evaluation process. It usually summarizes the main rules, standards, methods and procedures for bid evaluation, so that the bid evaluation committee can understand the key points of the bid evaluation work at a glance. Then, based on the bid evaluation method, the subjective evaluation items can be deconstructed. According to the different technical scoring standards in the bid evaluation method, the deconstructed subjective evaluation items include but are not limited to: supply and installation plan (10), technical review (20), product brand (6), financial audit report (3), localized service capability (3), free warranty period (4), energy saving (4), etc. Among them, the value in the brackets after each subjective evaluation item represents the total score of the corresponding subjective evaluation item. Taking the supply and installation plan (10) as an example, it means that according to the provisions of the bid evaluation method, the total score of this subjective evaluation item is 10 points.

[0104] In some embodiments of the present application, for the above step S130, each target AI expert is called to instruct the target AI expert to combine the scoring rules of each evaluation factor to illustrate the process of generating the scoring of the bid document in the evaluation factor.

[0105] In order to call the target AI expert to score the review factors, a prompt format template is designed in this embodiment. The prompt format template includes a task instruction, a bid document slot, a review factor slot, and a scoring rule slot. The task instruction is used to instruct the large model to find the corresponding content from the bid document in the bid document slot according to the review factors in the review factor slot, and score based on the scoring rules in the scoring rule slot.

[0106] Furthermore, the bid document of the current bidder is filled into the bid document slot, the review factor corresponding to the subjective review item is filled into the review factor slot, and the scoring rule corresponding to the review factor is filled into the scoring rule slot to obtain a first prompt instruction prompt. The first prompt instruction prompt is input to the target AI expert to obtain the score of the bid document of the current bidder in the review factor generated by the target AI expert.

[0107] The following takes the elevator bidding scenario as an example to provide an example of the first prompt instruction prompt:

[0108] prompt="You are an elevator bidding expert. Now you are given some bidding document fragments, and an evaluation factor and a scoring rule with corresponding standards. You need to find relevant content from the bidding document fragments based on the evaluation factor, and then give the corresponding score based on the scoring rule.

[0109] Bidding document excerpt: When supplying goods, our company will provide the purchaser with the certificate of the winning goods, equipment configuration list, user operation manual, etc. <ret>Manuals and maintenance manuals (Chinese version).

[0110] Evaluation elements: Warranty period service measures

[0111] Scoring rules: {'Level 1': 'Service measures during the warranty period are complete, which can effectively ensure the normal operation of the equipment and provide timely and effective services', 'Level 2': 'Service measures during the warranty period are basically complete, but the service response time is long, and there may be certain problems that cannot be solved in time', 'Level 3': 'Service measures during the warranty period are not complete, the service response time is long, and there is a risk that major problems cannot be solved in time'}

[0112] You are required to output the score and reason you gave, in the format of "{'score': the rating you gave, 'reason': the reason you gave this score.}".

[0113] Please note that the output scores must meet the requirements of the bid evaluation rules. Random scoring and plagiarism are prohibited. If you cannot give a score, please say that you cannot give a score and explain the reason. ".

[0114] The first prompt instruction prompt in the above example can also be used to instruct the large model to generate scoring reasons, thereby enhancing the interpretability and accuracy of the generated score.

[0115] In some embodiments of the present application, the aforementioned step S140 is described as to the process of determining the score of each target AI expert for the current bidder in the subjective review item based at least on a single basic score.

[0116] In one possible implementation, the single basic score can be directly determined as the score of the target AI expert on the current bidder on the subjective review item.

[0117] In other possible implementations, in order to improve the accuracy of the scoring results of the subjective review items, the scores of other dimensions can be further combined on the basis of the basic scores of the individual items to jointly determine the final scoring results.

[0118] In this embodiment, a horizontal comparison score is further provided. The horizontal comparison score can be obtained by comparing the individual basic scores of all bidders in the subjective evaluation items, classifying all bidders according to the size of the individual basic scores, and then determining the horizontal comparison score corresponding to each class.

[0119] The process of determining the current bidder's score on the subjective evaluation item may include:

[0120] S11. Obtain each bidder's individual basic score in the subjective evaluation item, and classify all bidders according to the individual basic score.

[0121] When classifying bidders according to the individual basic scores, the pre-set classification rules may be used. For example, according to the pre-set classification interval, bidders whose individual basic scores fall into the same classification interval are classified into the same classification interval. The classification interval can support flexible configuration. For example, different individual basic scores can be set to correspond to different classifications.

[0122] S12. Determine the horizontal comparison score corresponding to each level according to the total value of the configured horizontal comparison score, and obtain the horizontal comparison score corresponding to the level of the current bidder.

[0123] Specifically, the total score of each subjective review item can be specified. The total score of the subjective review item can be composed of the single basic score T1 and the horizontal comparison score T2. The proportion of the two can be the same or different, and can be flexibly configured by the user. After configuring the proportion of the horizontal comparison score T2, the total horizontal comparison score T2 can be obtained.

[0124] On this basis, the horizontal comparison scores corresponding to each level can be determined based on the total horizontal comparison score T2, and then the horizontal comparison score corresponding to the level of the current bidder can be obtained.

[0125] For example, all bidders are sorted from high to low into Tier 1 to Tier i. If the current bidder is in Tier a, the horizontal comparison corresponding to Tier a is divided into: T2-(a-1)×T2 / i.

[0126] S13. Add the current bidder's individual basic score in the subjective evaluation item and the current bidder's horizontal comparison score to obtain the current bidder's score in the subjective evaluation item.

[0127] Define the maximum score of the review factor generated by the target AI expert as Tmax. Taking the percentage system as an example, Tmax=100. Then the single basic score = (X1×W1+ X2×W2+…+ Xn×Wn)×T1 / Tmax. Among them, X1-Xn respectively represent the score of each review factor generated by each target AI expert, and W1-Wn respectively represent the attention weight of the target AI expert to each review factor.

[0128] After obtaining the current bidder's individual basic score and horizontal comparison score in the subjective evaluation item, the two can be added together to obtain the current bidder's score in the subjective evaluation item.

[0129] In this embodiment, a scoring mechanism is designed. On the basis of considering the single basic score generated by the target AI expert, a horizontal comparison score is further calculated to measure the difference between the current bidder and other bidders. On this basis, the single basic score and the horizontal comparison score are added together as the score of the current bidder in the subjective review item, making the scoring more scientific and reasonable.

[0130] In some other possible implementations, in order to improve the accuracy of the scoring results of the subjective review items, the divergent innovation score can be further considered on the basis of the single basic score and the horizontal comparison score to jointly determine the final scoring result.

[0131] In this embodiment, a divergent innovation score is further set to measure whether the bidder's bid document contains other feasible and reasonable innovative evaluation elements on the basis of the evaluation elements corresponding to the subjective evaluation items that have been given. In other words, it measures the divergent innovation ability of the bid document. Innovative thinking is encouraged, and extra points are given for outstanding performance beyond the conventional framework.

[0132] The process of determining the current bidder's score on the subjective evaluation item may include:

[0133] S21. Call each target AI expert to instruct the target AI expert to summarize the innovative evaluation factors that are feasible and reasonable, in addition to the evaluation factors corresponding to the subjective evaluation items, for the bid documents of the current bidder and the bid documents of other bidders, so as to obtain the innovative evaluation factors corresponding to each bidder generated by the target AI expert.

[0134] In this step, the target AI expert is called to summarize other feasible and reasonable innovative evaluation factors for each bidder's bid document, in addition to the evaluation factors corresponding to the given subjective evaluation items, so as to obtain the innovative evaluation factors summarized in each bidder's bid document as the corresponding innovative evaluation factors of the bidder.

[0135] S22. Determine the divergent innovation score of each bidder based on the number of innovation evaluation elements of each bidder.

[0136] In this step, the divergent innovation score of each bidder can be measured in combination with the number of innovation evaluation elements of each bidder.

[0137] In one possible implementation, all bidders can be classified according to the number of innovation evaluation elements.

[0138] According to the total value of the configured divergent innovation points, the divergent innovation points corresponding to each level are determined, and the divergent innovation points corresponding to the level of each bidder are obtained.

[0139] Specifically, the total score of the subjective review item can be composed of the single basic score T1, the horizontal comparison score T2 and the divergent innovation score T3. The proportions of the three can be the same or different, and can be flexibly configured by the user. For example, the proportion of the single basic score T1 is 70%, the proportion of the horizontal comparison score T2 is 20%, and the proportion of the divergent innovation score T3 is 10%. After configuring the proportions of the three scores, the total value of the divergent innovation score T3 can be obtained.

[0140] On this basis, the divergent innovation scores corresponding to each level can be determined based on the total value of the divergent innovation score T3, and then the divergent innovation score corresponding to the level of the current bidder can be obtained.

[0141] For example, all bidders are sorted from high to low into Tier 1 to Tier j. If the current bidder is in Tier a, then the divergent innovation corresponding to Tier a is divided into: T3-(a-1)×T3 / j.

[0142] S23. Add the current bidder's individual basic score in the subjective review item, the current bidder's horizontal comparison score and the current bidder's divergent innovation score to obtain the current bidder's score in the subjective review item.

[0143] In combination with the previous embodiment, after obtaining the individual basic score, horizontal comparison score and divergent innovation score of the current bidder in the subjective evaluation item, the three can be added together to obtain the score of the current bidder in the subjective evaluation item.

[0144] In this embodiment, another scoring mechanism is designed. On the basis of considering the single basic score and horizontal comparison score generated by the target AI expert, the divergent innovation score is further calculated to measure the divergent innovation ability of the current bidder's bid document relative to the bid documents of other bidders. On this basis, the three scores are added together as the score of the current bidder in the subjective review item, making the scoring more scientific and reasonable.

[0145] The following is a description of a device for evaluating subjective items in bidding and tendering provided in an embodiment of the present application. The device for evaluating subjective items in bidding and tendering described below and the method for evaluating subjective items in bidding and tendering described above can be referenced to each other.

[0146] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of a device for evaluating subjective items in bidding and tendering disclosed in an embodiment of the present application.

[0147] like Figure 6 As shown, the device may include:

[0148] The data acquisition unit 11 is used to acquire the bidding documents of the current bidder, and acquire the evaluation elements corresponding to the subjective evaluation items, and the scoring rules of the evaluation elements;

[0149] The AI ​​expert selection unit 12 is used to respond to the user's instruction to select an AI expert and determine the target AI expert selected by the user from the configured AI expert database, wherein different AI experts in the AI ​​expert database are large models trained with professional data in different fields;

[0150] A weight setting unit 13, configured to obtain the attention weight of each target AI expert to each review element in response to the user setting the attention weight of each review element for each target AI expert;

[0151] The AI ​​expert scoring unit 14 is used to call each of the target AI experts to instruct the target AI experts to generate a score for the bid document in the evaluation element in combination with the scoring rule for each of the evaluation elements;

[0152] The single basic score calculation unit 15 is used to perform weighted summation of the scores of each of the evaluation elements generated by each of the target AI experts according to the attention weights to obtain the single basic score of the current bidder in the subjective evaluation item.

[0153] The total score determination unit 16 is used to determine the score of each target AI expert for the current bidder in the subjective review item based at least on the single basic score.

[0154] In a possible implementation, the process of the total score determination unit determining the score of each target AI expert for the current bidder in the subjective review item based at least on the single basic score includes:

[0155] Obtaining the basic score of each bidder in the subjective evaluation item, and grading all bidders according to the basic score;

[0156] According to the total value of the configured horizontal comparison score, determine the horizontal comparison score corresponding to each level, and obtain the horizontal comparison score corresponding to the level of the current bidder;

[0157] The individual basic score of the current bidder in the subjective evaluation item and the horizontal comparison score of the current bidder are added together to obtain the score of the current bidder in the subjective evaluation item.

[0158] In a possible implementation, the process in which the total score determination unit determines the score of each target AI expert for the current bidder in the subjective review item based at least on the single basic score, further includes:

[0159] Calling each of the target AI experts to instruct the target AI experts to summarize the innovative evaluation factors with feasibility and rationality for the bid documents of the current bidder and the bid documents of other bidders, in addition to the evaluation factors corresponding to the subjective evaluation items, to obtain the innovative evaluation factors corresponding to each bidder generated by the target AI experts;

[0160] Determine the divergent innovation score of each bidder according to the number of innovation evaluation elements of each bidder;

[0161] The individual basic score of the current bidder in the subjective evaluation item, the horizontal comparison score of the current bidder and the divergent innovation score of the current bidder are added together to obtain the score of the current bidder in the subjective evaluation item.

[0162] In a possible implementation, the process of determining the divergent innovation score of each bidder by the total score determination unit according to the number of innovation evaluation elements of each bidder includes:

[0163] All bidders are classified according to the number of innovation evaluation elements mentioned;

[0164] According to the total value of the configured divergent innovation points, the divergent innovation points corresponding to each level are determined, and the divergent innovation points corresponding to the level of each bidder are obtained.

[0165] In a possible implementation, the apparatus of the present application may further include: a subjective evaluation item subdivision unit, configured to determine the subjective evaluation item based on the bid evaluation method in the bidding document before the data acquisition unit acquires each evaluation element corresponding to the subjective evaluation item and the scoring rule of the evaluation element;

[0166] The big model is called to instruct the big model to subdivide the subjective evaluation items according to the evaluation method in the bidding document to obtain the subdivided evaluation elements and corresponding scoring rules.

[0167] In a possible implementation, the AI ​​expert scoring unit calls the target AI expert to instruct the target AI expert to generate a scoring process for the bid document based on the evaluation element in combination with the scoring rule of each evaluation element, including:

[0168] Obtain a prompt format template of a prompt instruction, wherein the prompt format template includes a task instruction, a bid document slot, an evaluation factor slot, and a scoring rule slot, wherein the task instruction is used to instruct the large model to find corresponding content from the bid document in the bid document slot according to the evaluation factor in the evaluation factor slot, and to score based on the scoring rule in the scoring rule slot;

[0169] Fill the bid document of the current bidder into the bid document slot, fill the evaluation factors into the evaluation factor slot, fill the scoring rules corresponding to the evaluation factors into the scoring rule slot, obtain a first prompt instruction prompt, input the first prompt instruction prompt to the target AI expert, and obtain the score of the bid document generated by the target AI expert for the evaluation factors.

[0170] Optionally, the above task instructions are also used to instruct the large model to generate scoring reasons.

[0171] The present application also provides an electronic device in an embodiment. Figure 7 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, tablet computers, desktop computers, etc. Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0172] like Figure 7 As shown, the electronic device may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603, so as to implement the bidding subjective item evaluation method of the aforementioned embodiment of the present application. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0173] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0174] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the subjective item evaluation methods for bidding and tendering provided in the embodiments of the present application.

[0175] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any one of the subjective item evaluation methods for bidding and tendering provided in the embodiment of the present application.

[0176] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0177] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0178] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0179] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0180] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.< / ret>

Claims

1. A method for evaluating subjective items in bidding, characterized in that: include: Obtain the bidding documents of the current bidder, as well as the evaluation elements corresponding to the subjective evaluation items and the scoring rules of the evaluation elements; In response to the user's instruction to select an AI expert, determine the target AI expert selected by the user from a configured AI expert database, where different AI experts in the AI ​​expert database are large models trained using professional data in different fields; In response to the user setting the attention weight of each target AI expert to each review element, the attention weight of each target AI expert to each review element is obtained; Calling each of the target AI experts to instruct the target AI experts to generate a score of the bid document in the evaluation element in combination with the scoring rule of each of the evaluation elements; The scores of each of the evaluation factors generated by each of the target AI experts are weighted and summed according to the attention weight to obtain the individual basic score of the current bidder in the subjective evaluation item, and the score of the current bidder by each of the target AI experts in the subjective evaluation item is determined at least based on the individual basic score.

2. The method according to claim 1, characterized in that The process of determining the score of the current bidder in the subjective review item by each of the target AI experts based at least on the single basic score includes: Obtaining the basic score of each bidder in the subjective evaluation item, and classifying all bidders according to the basic score; According to the total value of the configured horizontal comparison score, determine the horizontal comparison score corresponding to each level, and obtain the horizontal comparison score corresponding to the level of the current bidder; The individual basic score of the current bidder in the subjective evaluation item and the horizontal comparison score of the current bidder are added together to obtain the score of the current bidder in the subjective evaluation item.

3. The method according to claim 2, characterized in that Also includes: Calling each of the target AI experts to instruct the target AI experts to summarize the innovative evaluation factors with feasibility and rationality for the bid documents of the current bidder and the bid documents of other bidders, in addition to the evaluation factors corresponding to the subjective evaluation items, to obtain the innovative evaluation factors corresponding to each bidder generated by the target AI experts; Determine the divergent innovation score of each bidder according to the number of innovation evaluation elements of each bidder; The individual basic score of the current bidder in the subjective evaluation item, the horizontal comparison score of the current bidder and the divergent innovation score of the current bidder are added together to obtain the score of the current bidder in the subjective evaluation item.

4. The method according to claim 3, characterized in that The process of determining each bidder’s divergent innovation score based on the number of innovation evaluation elements for each bidder includes: All bidders are classified according to the number of innovation evaluation elements mentioned; According to the total value of the configured divergent innovation points, the divergent innovation points corresponding to each level are determined, and the divergent innovation points corresponding to the level of each bidder are obtained.

5. The method according to claim 1, characterized in that Before obtaining the evaluation factors corresponding to the subjective evaluation items and the scoring rules of the evaluation factors, it also includes: Determine the subjective evaluation items based on the bid evaluation method in the bidding documents; The big model is called to instruct the big model to subdivide the subjective evaluation items according to the evaluation method in the bidding document to obtain the subdivided evaluation elements and corresponding scoring rules.

6. The method according to claim 1, characterized in that The process of calling the target AI expert to instruct the target AI expert to generate the score of the bid document in the evaluation element in combination with the scoring rule of each evaluation element includes: Obtain a prompt format template of a prompt instruction, wherein the prompt format template includes a task instruction, a bid document slot, an evaluation factor slot, and a scoring rule slot, wherein the task instruction is used to instruct the large model to find corresponding content from the bid document in the bid document slot according to the evaluation factor in the evaluation factor slot, and to score based on the scoring rule in the scoring rule slot; Fill the bid document of the current bidder into the bid document slot, fill the evaluation factors into the evaluation factor slot, fill the scoring rules corresponding to the evaluation factors into the scoring rule slot, obtain a first prompt instruction prompt, input the first prompt instruction prompt to the target AI expert, and obtain the score of the bid document generated by the target AI expert for the evaluation factors.

7. The method according to claim 6, characterized in that The task instructions are also used to instruct the large model to generate scoring reasons.

8. A device for evaluating subjective items in bidding, characterized in that: include: A data acquisition unit, used to acquire the bidding documents of the current bidder, and to acquire the evaluation elements corresponding to the subjective evaluation items, and the scoring rules of the evaluation elements; An AI expert selection unit, configured to respond to an instruction from a user to select an AI expert and determine a target AI expert selected by the user from a configured AI expert database, wherein different AI experts in the AI ​​expert database are large models trained using professional data from different fields; A weight setting unit, configured to obtain the attention weight of each target AI expert to each review element in response to the user setting the attention weight of each review element for each target AI expert; An AI expert scoring unit, configured to call each of the target AI experts to instruct the target AI experts to generate a score for the bid document in the evaluation element in combination with a scoring rule for each of the evaluation elements; A single basic score calculation unit, used to perform weighted summation of the scores of each of the evaluation elements generated by each of the target AI experts according to the attention weight, to obtain the single basic score of the current bidder in the subjective evaluation item; The total score determination unit is used to determine the score of each target AI expert for the current bidder in the subjective review item based at least on the single basic score.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the bidding subjective item evaluation method as described in any one of claims 1 to 7.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for evaluating subjective items in bidding and tendering as described in any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, each step of the subjective item evaluation method for bidding as described in any one of claims 1 to 7 is implemented.

Images