Information screening method and system for bid invitation platform
By using prefix tree matching and user portrait scoring technology on the bidding platform, the bidding information is screened and sorted in multiple levels, and the problems of low information search efficiency and low user satisfaction in the existing technology are solved, achieving efficient, accurate and personalized information screening effect.
Patent Information
- Application Number
- CN202510030883.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-08
- Publication Date
- 2025-05-02
AI Technical Summary
The information search efficiency of existing bidding platforms is low, and the user satisfaction of matching results is low, making it difficult to achieve efficient information screening through artificial intelligence technology.
By acquiring and preprocessing bidding information, using prefix tree matching and user portrait scoring technology, multi-level screening and sorting of bidding information is achieved, and the accuracy and efficiency of information screening are improved.
It improves the accuracy and efficiency of information screening, improves user satisfaction, increases the user retention rate and activity of the bidding platform, and can effectively handle large-scale and different formats of bidding information.
Smart Images
Figure CN119919219A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of information screening, and in particular to an information screening method and system, electronic equipment and storage medium for a bidding platform. Background Art
[0002] Artificial intelligence is a technology that simulates and extends human intelligence, aiming to create computer systems that can learn, reason, solve problems, and perform tasks autonomously. In the past few years, advances in artificial intelligence technology have begun to change the way we live, and it is expected that it will continue to affect all aspects of our lives. A neural network model is a computational model based on artificial neurons, which mimics the connections and information transmission between neurons in the human brain. A neural network model usually consists of multiple hidden layers, which can help the neural network extract more complex patterns and structures from input features. The neural network model is one of the core technologies of artificial intelligence and is widely used in natural language processing, image recognition, speech recognition, self-driving cars, smart homes, and security.
[0003] A bidding platform is an online platform that is specifically used to publish and manage bidding information, helping the bidding party (usually a government agency, enterprise, institution, etc.) and the bidder (supplier, contractor, etc.) to achieve efficient communication and transactions. A bidding platform generally includes: information publishing, information collection, user registration and management, search and screening, etc.
[0004] At present, information search on bidding platforms generally uses regular matching, which is inefficient and has low user satisfaction with matching results.
[0005] To sum up, how to apply artificial intelligence technology to information screening on bidding platforms to obtain screening results with higher user satisfaction is an issue that needs to be resolved. Summary of the invention
[0006] In view of this, the embodiments of the present disclosure provide an information screening method and system for a bidding platform, an electronic device and a storage medium, which perform information screening for a bidding platform through artificial intelligence technology.
[0007] In a first aspect, the embodiments of the present disclosure provide an information screening method for a bidding platform, which adopts the following technical solutions: Acquire the tender information to be screened, pre-process the acquired tender information to form a tender information set to be screened, wherein each piece of tender information included in the tender information set to be screened includes a plurality of fields having a corresponding relationship; Performing a primary screening on multiple fields in the bidding information set to be screened according to the keywords input by the user to obtain a primary screening information set; Sort the bidding information in the first-level screening information set based on the user portrait to obtain the second-level screening information set; The secondary screening information set is sent to the display module, so that the display module can display the bidding information therein according to the order of the secondary screening information set.
[0008] As an optional implementation, the first-level screening of multiple fields in the bidding information set to be screened according to the keywords input by the user includes: Build a prefix tree based on the keywords entered by the user. Build a keyword path for each keyword, and use the first character of the keyword as the child node of the root node of the prefix tree. Calculate the failover path for each node in the prefix tree; The information in the bidding information set to be screened is read and matched with the prefix tree. If the match is successful, the last node of the keyword records the position of the matched keyword in the bidding information set. If the match fails, it is transferred to other nodes according to the failure transfer path.
[0009] As an optional implementation, the sorting of the bidding information in the first-level screening information set based on the user portrait includes: Get user portraits; Use user portraits to score each bidding information in the first-level screening information set; Get the ranking method of user preferences; Each bidding information in the first-level screening information set is sorted in descending order according to the scoring results and the sorting method of user preferences.
[0010] As an optional implementation, using the user portrait to score each bidding information in the first-level screening information set includes calculating the score according to the following formula: , in, Indicates the scoring result of bidding information b. Represents the score of the b-th bidding information given by the t-th decision tree.
[0011] As an optional implementation, the obtaining of the user portrait includes: Check whether the user's browsing history and search history are available; If not, then The answers to the preset questions filled in by the user when registering the system are used to train the random forest model to obtain the user portrait; If so, then Determine whether the user's browsing history and search history have been used as training data to train the user profile; If the user's browsing history and search history have not been used as training data to train the user profile, the user's browsing history and search history are used as correction data to train the original user profile to obtain a new user profile.
[0012] As an optional implementation manner, the preprocessing of the acquired bidding information to form a bidding information set to be screened includes: Identify spelling errors using a deep learning algorithm model annotated with a proprietary vocabulary; Convert data in different formats into a unified format through predefined mapping tables; The processed bidding information is stored in a designated location according to a predetermined format and sequence to form a bidding information set to be screened.
[0013] In a second aspect, the embodiments of the present disclosure further provide an information screening system for a bidding platform, including: A bidding information acquisition and preprocessing module acquires the bidding information to be screened, preprocesses the acquired bidding information, and forms a bidding information set to be screened, wherein each piece of bidding information included in the bidding information set to be screened includes a plurality of fields having a corresponding relationship; A primary screening module, performing primary screening on multiple fields in the bidding information set to be screened according to keywords input by a user, to obtain a primary screening information set; The secondary screening module sorts the bidding information in the primary screening information set based on the user portrait to obtain the secondary screening information set; The sending module sends the secondary screening information set to the display module, so that the display module can display the bidding information therein according to the sorting of the secondary screening information set.
[0014] As an optional implementation, the secondary screening module includes: User portrait acquisition module, to obtain user portrait; The scoring module uses user portraits to score each bidding information in the first-level screening information set; Sorting method acquisition module, which obtains the sorting method preferred by users; The sorting module arranges each bidding information in the first-level screening information set in descending order according to the scoring results and the sorting method preferred by the user.
[0015] In a third aspect, the present disclosure also provides an electronic device, which adopts the following technical solution: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the above-mentioned information screening methods for a bidding platform.
[0016] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute any of the above-mentioned information screening methods for a bidding platform.
[0017] In summary, the technical effects of the information screening method for a bidding platform provided by the present disclosure are: The information screening method for the bidding platform provided by the embodiment of the present disclosure integrates multiple steps such as data preprocessing, keyword matching, and user portrait scoring, aiming to improve the accuracy and efficiency of information screening. The screening efficiency and accuracy of bidding information are optimized from multiple angles. The quality of the data is improved by preprocessing of the deep learning algorithm model, the prefix tree matching mechanism ensures the speed and accuracy of keyword screening, and the application of user portrait technology makes the screening results more in line with the personalized needs of users. This not only improves user satisfaction, but also brings higher user retention rate and activity to the bidding platform itself. In addition, the method is particularly effective for processing large-scale and formatted bidding information, and can support the bidding platform to maintain good performance and service quality when facing more and more information. In summary, this is an efficient, accurate and personalized information screening solution, which has important practical significance for promoting the rational use of bidding information and optimizing user experience.
[0018] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following preferred embodiments are specifically cited and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0020] Figure 1 A flowchart of an information screening method for a bidding platform provided in an embodiment of the present disclosure; Figure 2 A schematic diagram of the structure of an information screening system for a bidding platform provided in an embodiment of the present disclosure; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0021] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
[0022] It should be clear that the following embodiments of the present disclosure are described by specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.
[0023] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.
[0024] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.
[0025] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.
[0026] Reference Figure 1 The first aspect of the present invention provides an information screening method for a bidding platform, comprising: Step S1, obtaining the tender information to be screened, preprocessing the obtained tender information to form a tender information set to be screened, wherein each piece of tender information contained in the tender information set to be screened includes a plurality of fields having a corresponding relationship; different fields represent different information of the tender project, for example, including: Title: The name of the bidding project.
[0027] Description: Description of the content of the bidding project.
[0028] Budget: The budget amount for the project.
[0029] Category: The category of the project (such as construction engineering, IT services, equipment procurement, etc.).
[0030] Location: The location where the project will be implemented.
[0031] Tenderer: The organization or company that publishes the tender information.
[0032] Release time: the release time of the bidding information.
[0033] As an optional implementation, the preprocessing of the acquired bidding information to form a bidding information set to be screened includes: Step S11, preferably using a deep learning algorithm model annotated with a proprietary vocabulary to identify spelling errors; in addition to the deep learning algorithm model, the following methods can also be used to identify spelling errors: Levenshtein distance, Damerau-Levenshtein distance, BK-Tree, N-gram, etc.
[0034] Step S12, converting data in different formats into a unified format through a predefined mapping table; this can also be achieved using a regular expression.
[0035] Step S13, storing the processed bidding information in a designated location according to a predetermined format and sequence to form a bidding information set to be screened.
[0036] The technical effect of this step is that, firstly, by identifying and correcting spelling errors through the deep learning algorithm model, it is possible to eliminate screening omissions or errors caused by spelling errors, thereby improving the accuracy of the data and the reliability of subsequent screening; secondly, the use of predefined mapping tables to standardize the data format helps to reduce the difficulty of data processing and system complexity caused by inconsistent information formats, while also providing a clearer and more standardized data basis for subsequent primary and secondary screening; finally, storing the processed information in a predetermined format and order not only facilitates the management and search of information, but also greatly simplifies the data reading and writing process and speeds up data processing, which is particularly important for large-scale data processing.
[0037] Step S2, performing primary screening on multiple fields in the bidding information set to be screened according to the keywords input by the user to obtain a primary screening information set; As an optional implementation, the first-level screening of multiple fields in the bidding information set to be screened according to the keywords input by the user includes: Step S21, constructing a prefix tree according to the keywords input by the user, constructing a keyword path for each keyword, and the first character of the keyword as a child node of the root node of the prefix tree; Step S22, calculating the failover path of each node in the prefix tree; for example, including: 1. First, use breadth-first search (BFS) to traverse all nodes in the Trie tree and calculate the failure pointer of each node.
[0038] 2. Calculate the failure pointer of the child node: For direct child nodes of the root node, the failure pointer points to the root node.
[0039] For other nodes, assume that the parent node of the current node is p, the current node is a child node c of p, and the failure pointer of p points to node f. Then, the failure pointer of c can be calculated by the following steps: Starting from node f, follow the path of the child nodes of node f to find out whether there is a child node whose character is the same as the character of node c.
[0040] If there is such a child node s, the failure pointer of c points to s.
[0041] If there is no such child node, continue to jump along the failure pointer of node f and repeat the above search process until a suitable child node is found or jump to the root node. If you finally jump to the root node and still cannot find a suitable child node, the failure pointer of c points to the root node.
[0042] Step S23, read the information in the bidding information set to be screened and match it with the prefix tree. If the match is successful, the last node of the keyword records the position of the matched keyword in the bidding information set. If the match fails, transfer to other nodes according to the failure transfer path.
[0043] In the matching process, the root node is matched first. The child nodes of the root node are the first word of each keyword. The second word of each keyword is the child node of the first word, and so on. When any child node under the root node is matched, the child node is entered and the child nodes of the child node are matched until the keyword matches the node where the last word is located. The match is successful, and the last node of the keyword records the position of the matched keyword in the bidding information set.
[0044] In this step, a prefix tree is used to construct a keyword matching mechanism and calculate the failure path to achieve efficient and accurate screening. The purpose of using a prefix tree is to improve the speed and efficiency of keyword matching, because it can quickly locate information items that match the keywords entered by the user, and maintain a high response speed even when processing large amounts of data. The purpose of calculating the failure path is to quickly skip the unmatched content when no match is found, which not only improves the screening efficiency, but also enhances the user experience of the system. Through this efficient processing method, the first-level screening can provide users with a set of qualified bidding information in a very short time, greatly saving the user's time cost.
[0045] Step S3, sorting the bidding information in the first-level screening information set based on the user portrait to obtain a second-level screening information set; As an optional implementation, the sorting of the bidding information in the first-level screening information set based on the user portrait includes: Step S31, obtaining a user portrait; As an optional implementation, the obtaining of the user portrait includes: Check whether the user's browsing history and search history are available; If not, then The answers to the preset questions filled in by the user when registering the system are used to train the random forest model to obtain the user portrait; If so, then Determine whether the user's browsing history and search history have been used as training data to train the user profile; If the user's browsing history and search history have not been used as training data to train the user profile, the user's browsing history and search history are used as correction data to train the original user profile to obtain a new user profile.
[0046] Step S32, using the user portrait to score each bidding information in the first-level screening information set; Specifically, using the user profile to score each bidding information in the first-level screening information set includes calculating the score according to the following formula: , in, Indicates the scoring result of bidding information b. Represents the score of the b-th bidding information given by the t-th decision tree.
[0047] Step S33, obtaining the sorting method of user preferences; the sorting methods of user preferences include: time priority sorting, popularity priority sorting, user feedback priority sorting (generally referring to giving priority to displaying those with good user feedback), etc.
[0048] For example, the ranking methods for obtaining user preferences include: The user's feature data and historical behavior data are input into the sorting method model to obtain the sorting method output by the model.
[0049] For example, the sorting model training and application are as follows.
[0050] 1. Data Collection First, a large amount of user behavior data needs to be collected. This data may include but is not limited to the following: User characteristic data: user’s personal information (such as age, gender, industry, position, etc.), registration time, activity level, etc.
[0051] Historical behavior data: user’s search history, click history, favorite history, sharing history, dwell time, etc.
[0052] Bidding information characteristic data: project type, bidding amount, bidding time, technical requirements, etc.
[0053] User feedback data: user satisfaction ratings, comments, complaints, etc.
[0054] 2. Data Preprocessing Data preprocessing is a key step to ensure data quality, including: Data cleaning: Remove invalid, duplicate or erroneous data.
[0055] Data normalization: Normalize data of different dimensions so that they are within the same range to facilitate subsequent calculations.
[0056] Feature selection: Select the features most relevant to the ranking preference to reduce model complexity and improve prediction accuracy.
[0057] 3. Feature Engineering Feature engineering is to generate features useful for model training through data processing and transformation. The specific steps include: User feature extraction: Extract useful features from the user's personal information, such as the user's industry, position, etc.
[0058] Historical behavior feature extraction: Extract useful features from users’ historical behavior data, such as users’ click-through rates for different item types, users’ average stay time on search results pages, etc.
[0059] Tender information feature extraction: Extract useful features from tender information, such as the frequency of project types, the distribution of tender amounts, etc.
[0060] 4. Model Training Choose an appropriate machine learning model to train the user behavior model. Commonly used models include: Logistic regression: Applicable to binary classification problems, it can predict whether users prefer time priority or popularity priority.
[0061] Decision trees: can handle multiple feature types and can intuitively show the impact of each feature on user preferences.
[0062] Random Forest: Improve the stability and accuracy of the model through an ensemble of multiple decision trees.
[0063] Deep learning models (such as multi-layer perceptron MLP, neural networks, etc.): can capture complex feature relationships and are suitable for large-scale and complex data sets.
[0064] 5. Model selection and optimization By comparing the performance of different models, the best model can be selected. Common evaluation indicators include: Accuracy: The proportion of correctly predicted results.
[0065] Precision: The proportion of samples predicted to be of a certain class that actually belong to that class.
[0066] Recall: The proportion of samples of a certain class that are correctly predicted.
[0067] F1 score: The harmonic mean of precision and recall.
[0068] The cross-validation method can be used to evaluate the performance of the model and optimize the model by adjusting model parameters, adding features, reducing noise data, etc.
[0069] 6. User Preference Prediction After the model training is completed, the model is used to predict user preferences. The specific steps are as follows: Input user data: Input the user’s feature data and historical behavior data into the model.
[0070] Output preference labels: The model outputs labels indicating whether the user prefers time-first sorting or heat-first sorting.
[0071] Adjust sorting strategy: Adjust the sorting strategy of search results based on the model's prediction results.
[0072] 7. Dynamically adjust sorting weights Dynamically adjust the sorting weight based on the user's preference prediction results. For example: If the model predicts that the user prefers time first, the weight of timestamp can be increased.
[0073] If the model predicts that users prefer popularity first, you can increase the weight of popularity.
[0074] 8. Real-time feedback and updates User behaviors and preferences change dynamically, so the user behavior model needs to be updated regularly to adapt to user changes. The specific steps include: Real-time data collection: Continuously collect users' real-time behavior data, such as new click records, search records, etc.
[0075] Model retraining: Regularly retrain the user behavior model with new data to maintain the accuracy and effectiveness of the model.
[0076] User experience monitoring: Monitor the effectiveness of the sorting strategy through user feedback (such as click-through rate, satisfaction score, etc.), and continuously optimize the model and sorting strategy.
[0077] Step S34, sorting each bidding information in the first-level screening information set in descending order according to the scoring results combined with the user's preferred sorting method. Specifically, this step prioritizes sorting in descending order according to the scoring results, and sorting according to the user's preferred sorting method when the scoring results are the same.
[0078] In this step, the trained random forest model is used. The information filled in by the user during registration is first used for preliminary training, and then the model is continuously revised based on the user's browsing history and search history to more accurately reflect the user's preferences. The user portrait is used for scoring, and the scored data is sorted and displayed in combination with the user's preferred sorting method, so that the bidding information finally presented to the user is closer to his or her actual needs. The advantage of this method is that it can dynamically adapt to changes in user interests. Over time, the information recommendations obtained by the user will become more and more accurate, thereby improving the level of personalization of information screening and user satisfaction.
[0079] Step S4, sending the secondary screening information set to the display module, so that the display module displays the bidding information therein according to the order of the secondary screening information set.
[0080] In this step, the secondary screening information set is sent to the display module, which displays the bidding information therein according to the order of the information set. This step ensures that the information is displayed in the order of user preference, which not only enhances the readability and ease of use of the information, but also further improves the overall user experience on the platform.
[0081] In summary, the information screening method for the bidding platform provided by the present invention integrates multiple steps such as data preprocessing, keyword matching, and user portrait scoring, aiming to improve the accuracy and efficiency of information screening. The screening efficiency and accuracy of bidding information are optimized from multiple angles. The quality of data is improved by preprocessing of the deep learning algorithm model, the prefix tree matching mechanism ensures the speed and accuracy of keyword screening, and the application of user portrait technology makes the screening results more in line with the personalized needs of users. This not only improves user satisfaction, but also brings higher user retention rate and activity to the bidding platform itself. In addition, the method is particularly effective for processing large-scale and formatted bidding information, and can support the bidding platform to maintain good performance and service quality when facing more and more information. In summary, this is an efficient, accurate and personalized information screening solution, which has important practical significance for promoting the rational use of bidding information and optimizing user experience.
[0082] On the other hand, refer to Figure 2 The present invention provides an information screening system for a bidding platform, comprising: A bidding information acquisition and preprocessing module acquires the bidding information to be screened, preprocesses the acquired bidding information, and forms a bidding information set to be screened, wherein each piece of bidding information included in the bidding information set to be screened includes a plurality of fields having a corresponding relationship; A primary screening module, performing primary screening on multiple fields in the bidding information set to be screened according to keywords input by a user, to obtain a primary screening information set; The secondary screening module sorts the bidding information in the primary screening information set based on the user portrait to obtain the secondary screening information set; The sending module sends the secondary screening information set to the display module, so that the display module can display the bidding information therein according to the sorting of the secondary screening information set.
[0083] As an optional implementation, the secondary screening module includes: User portrait acquisition module, to obtain user portrait; The scoring module uses user portraits to score each bidding information in the first-level screening information set; Sorting method acquisition module, which obtains the sorting method preferred by users; The sorting module arranges each bidding information in the first-level screening information set in descending order according to the scoring results and the sorting method preferred by the user.
[0084] The electronic device according to an embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc.
[0085] The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In one embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, so that the electronic device performs all or part of the steps of the information screening method for the bidding platform in the aforementioned embodiments of the present disclosure.
[0086] Those skilled in the art should be able to understand that in order to solve the technical problem of how to obtain a good user experience, the present embodiment may also include well-known structures such as a communication bus and an interface, and these well-known structures should also be included in the protection scope of the present disclosure.
[0087] like Figure 3 The present invention provides a schematic diagram of the structure of an electronic device according to an embodiment of the present invention, which is suitable for implementing the electronic device in the embodiment of the present invention. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0088] like Figure 3 As shown, the electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processor, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.
[0089] Typically, the following devices can be connected to the I / O interface: input devices such as sensors or visual information acquisition devices; output devices such as display screens; storage devices such as tapes, hard disks, etc.; and communication devices. The communication device allows the electronic device to communicate with other devices (such as edge computing devices) wirelessly or by wire to exchange data. Figure 3An 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.
[0090] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of the information screening method for a bidding platform of an embodiment of the present disclosure are executed.
[0091] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.
[0092] According to the computer-readable storage medium of the embodiment of the present disclosure, non-transitory computer-readable instructions are stored thereon. When the non-transitory computer-readable instructions are executed by a processor, all or part of the steps of the information screening method for a bidding platform of the above-mentioned embodiments of the present disclosure are executed.
[0093] The above-mentioned computer-readable storage media include, but are not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (e.g., memory card) and media with built-in ROM (e.g., ROM box).
[0094] For detailed description of this embodiment, reference may be made to the corresponding descriptions in the aforementioned embodiments, which will not be repeated here.
[0095] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.
[0096] In the present disclosure, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. The block diagrams of the devices, devices, equipment, and systems involved in the present disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.
[0097] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.
[0098] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.
[0099] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.
[0100] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
[0101] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.
Claims
1. An information screening method for a bidding platform, characterized in that: include: Acquire the tender information to be screened, pre-process the acquired tender information to form a tender information set to be screened, wherein each piece of tender information included in the tender information set to be screened includes a plurality of fields having a corresponding relationship; Performing a primary screening on multiple fields in the bidding information set to be screened according to the keywords input by the user to obtain a primary screening information set; Sort the bidding information in the first-level screening information set based on the user portrait to obtain the second-level screening information set; The secondary screening information set is sent to the display module, so that the display module can display the bidding information therein according to the order of the secondary screening information set.
2. The information screening method for a bidding platform according to claim 1, characterized in that: The first-level screening of the multiple fields in the bidding information set to be screened according to the keywords input by the user includes: Build a prefix tree based on the keywords entered by the user. Build a keyword path for each keyword, and use the first character of the keyword as the child node of the root node of the prefix tree. Calculate the failover path for each node in the prefix tree; The information in the bidding information set to be screened is read and matched with the prefix tree. If the match is successful, the last node of the keyword records the position of the matched keyword in the bidding information set. If the match fails, it is transferred to other nodes according to the failure transfer path.
3. The information screening method for a bidding platform according to claim 2, characterized in that: The sorting of the bidding information in the first-level screening information set based on the user portrait includes: Get user portraits; Use user portraits to score each bidding information in the first-level screening information set; Get the ranking method of user preferences; Each bidding information in the first-level screening information set is sorted in descending order according to the scoring results and the sorting method of user preferences.
4. The information screening method for a bidding platform according to claim 3, characterized in that: Using the user portrait to score each bidding information in the first-level screening information set includes calculating the score according to the following formula: ， in, Indicates the scoring result of bidding information b. Represents the score of the b-th bidding information given by the t-th decision tree.
5. The information screening method for a bidding platform according to claim 4, characterized in that: The obtaining of the user portrait comprises: Check whether the user's browsing history and search history are available; If not, then The answers to the preset questions filled in by the user when registering the system are used to train the random forest model to obtain the user portrait; If so, then Determine whether the user's browsing history and search history have been used as training data to train the user profile; If the user's browsing history and search history have not been used as training data to train the user profile, the user's browsing history and search history are used as correction data to train the original user profile to obtain a new user profile.
6. The information screening method for a bidding platform according to claim 5, characterized in that: The preprocessing of the acquired bidding information to form a bidding information set to be screened includes: Identify spelling errors using a deep learning algorithm model annotated with a proprietary vocabulary; Convert data in different formats into a unified format through predefined mapping tables; The processed bidding information is stored in a designated location according to a predetermined format and sequence to form a bidding information set to be screened.
7. An information screening system for a bidding platform, characterized in that: include: A bidding information acquisition and preprocessing module acquires the bidding information to be screened, preprocesses the acquired bidding information, and forms a bidding information set to be screened, wherein each piece of bidding information included in the bidding information set to be screened includes a plurality of fields having a corresponding relationship; A primary screening module, performing primary screening on multiple fields in the bidding information set to be screened according to keywords input by a user, to obtain a primary screening information set; The secondary screening module sorts the bidding information in the primary screening information set based on the user portrait to obtain the secondary screening information set; The sending module sends the secondary screening information set to the display module, so that the display module can display the bidding information therein according to the sorting of the secondary screening information set.
8. The information screening system for a bidding platform according to claim 7, characterized in that: The secondary screening module comprises: User portrait acquisition module, to obtain user portraits; The scoring module uses user portraits to score each bidding information in the first-level screening information set; Sorting method acquisition module, which obtains the sorting method preferred by users; The sorting module arranges each bidding information in the first-level screening information set in descending order according to the scoring results and the sorting method preferred by the user.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the information screening method for a bidding platform as described in any one of claims 1-6.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the information screening method for a bidding platform as described in any one of claims 1-6.