Portable bid evaluation conference site management equipment

Abstract

The invention discloses portable bid evaluation conference site management equipment, and the equipment comprises a terminal collection module which is used for carrying out the identity information recognition of participants, obtains recognition data, and specifically comprises a face recognition unit, a two-dimensional code scanning unit, and an identity card reading unit; the face recognition unit is used for performing face recognition on participants based on a strong classifier to obtain face feature recognition data; the two-dimensional code scanning unit is used for identifying two-dimensional codes of participants to obtain two-dimensional code information identification data; the identity card reading unit is used for identifying identity cards of participants based on a built-in RFID radio frequency assembly to obtain identity card information identification data; the core algorithm module is used for analyzing the identification data, determining identities and matched participants based on an analysis result, and grouping the matched participants according to a preset bid evaluation personnel category to obtain a grouping result; and the user interaction module is used for outputting an information input interface comprising a grouping result.

Description

Technical Field

[0001] The present application relates to the technical field of bid evaluation management, and in particular to a portable on-site management device for bid evaluation meetings. Background Art

[0002] Bid evaluation meetings are a critical step in the bidding and evaluation process for various projects. The standardization and efficiency of their on-site management are directly related to the fairness and accuracy of the evaluation results and the smooth progress of the project. Traditional on-site management methods for bid evaluation meetings have many drawbacks and are unable to meet the growing demands of modern bid evaluation work.

[0003] On the one hand, traditional methods for verifying participant identities rely heavily on manual verification of IDs and work permits. This approach is not only inefficient and prone to misidentification due to negligence, but also fails to effectively prevent violations such as impersonation. On the other hand, traditional methods for managing participant grouping often rely on manual recording and classification, a cumbersome and error-prone process. Different bid evaluation projects have different requirements for participant classification and grouping. Manual operations are difficult to quickly and accurately group according to pre-set bid evaluation categories, resulting in confusing grouping results. Furthermore, manual grouping methods lack flexibility, making it difficult to adjust grouping strategies based on actual conditions and adapting to complex and changing bid evaluation scenarios. Furthermore, traditional methods for data entry typically require participants to fill out their personal information on paper forms, which are then manually entered into the system by staff. This approach not only increases staff workload but is also prone to data entry errors. Summary of the Invention

[0004] In view of this, the present application provides a portable site management device for bid evaluation meetings, which improves the accuracy and reliability of identity recognition by combining face recognition, QR code scanning and ID card reading, and can effectively prevent violations such as impersonation; the core algorithm module can automatically group participants according to the preset bid evaluation personnel categories corresponding to each bid evaluation meeting, thereby improving the efficiency, accuracy and flexibility of meeting management; the portable site management device for bid evaluation meetings adopts a portable design, which is convenient for deployment and use at different bid evaluation meeting sites, reducing the cost and difficulty of meeting organization.

[0005] According to one aspect of the present application, a portable bid evaluation meeting on-site management device is provided, comprising a terminal acquisition module, a core algorithm module, and a user interaction module;

[0006] The terminal acquisition module is used to identify the identity information of the participants and obtain identification data, wherein the terminal acquisition module includes a face recognition unit, a QR code scanning unit and an ID card reading unit; the face recognition unit is used to perform face recognition on the participant based on a strong classifier composed of multiple weak classifiers to obtain facial feature recognition data; the QR code scanning unit is used to identify the QR code of the participant based on a quick response matrix code to obtain QR code information recognition data; the ID card reading unit is used to identify the identification document of the participant based on a built-in RFID radio frequency component to obtain ID card information recognition data; the recognition data includes the facial feature recognition data, QR code information recognition data and ID card information recognition data;

[0007] The core algorithm module is used to analyze the identification data, determine participants whose identities match the current bid evaluation meeting based on the analysis results, and group the matched participants according to preset bid evaluation personnel categories corresponding to the current bid evaluation meeting to obtain grouping results;

[0008] The user interaction module is used to output an information entry interface including the grouping results, so that the participants can input personal information based on the information entry interface.

[0009] By means of the above technical solution, the present application provides a portable site management device for bid evaluation meetings, in which the terminal acquisition module is responsible for identifying the identity information of the participants and integrating the various data obtained by identification to form identification data. It includes a face recognition unit, a QR code scanning unit, and an ID card reading unit to obtain identity-related information of the participants through different technical means. Ultimately, the facial feature recognition data output by the face recognition unit, the QR code information recognition data output by the QR code scanning unit, and the ID card information recognition data output by the ID card reading unit can be used together as identification data to provide data support for the subsequent core algorithm module. The core algorithm module then analyzes the identification data obtained by the terminal acquisition module to determine whether the identity of the participant matches the current bid evaluation meeting, and groups the matched participants according to the preset bid evaluation personnel categories to obtain the grouping results. The user interaction module generates a corresponding information entry interface based on the grouping results obtained by the core algorithm module. The interface can display the group information of the participants and the personal information fields that need to be entered. The embodiment of the present application improves the accuracy and reliability of identity recognition by combining three methods: face recognition, QR code scanning and ID card reading, and can effectively prevent violations such as impersonation; the core algorithm module can automatically group participants according to the preset evaluator categories corresponding to each bid evaluation meeting, thereby improving the efficiency, accuracy and flexibility of meeting management; the portable bid evaluation meeting site management equipment adopts a portable design, which is convenient for deployment and use at different bid evaluation meeting sites, reducing the cost and difficulty of meeting organization.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, 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 application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0012] Figure 1 A schematic structural diagram of a portable bid evaluation meeting site management device provided in an embodiment of the present application is shown;

[0013] Figure 2 A flow chart illustrating a method for using a portable bid evaluation meeting on-site management device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0014] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0015] In this embodiment, a portable bidding meeting site management device is provided, such as Figure 1 As shown, the device includes a terminal acquisition module, a core algorithm module and a user interaction module;

[0016] The terminal acquisition module is used to identify the identity information of the participants and obtain identification data, wherein the terminal acquisition module includes a face recognition unit, a QR code scanning unit and an ID card reading unit; the face recognition unit is used to perform face recognition on the participant based on a strong classifier composed of multiple weak classifiers to obtain facial feature recognition data; the QR code scanning unit is used to identify the QR code of the participant based on a quick response matrix code to obtain QR code information recognition data; the ID card reading unit is used to identify the identification document of the participant based on a built-in RFID radio frequency component to obtain ID card information recognition data; the recognition data includes the facial feature recognition data, QR code information recognition data and ID card information recognition data;

[0017] The core algorithm module is used to analyze the identification data, determine participants whose identities match the current bid evaluation meeting based on the analysis results, and group the matched participants according to preset bid evaluation personnel categories corresponding to the current bid evaluation meeting to obtain grouping results;

[0018] The user interaction module is used to output an information entry interface including the grouping results, so that the participants can input personal information based on the information entry interface.

[0019] The portable bid evaluation meeting site management device provided in the present embodiment mainly consists of three parts: a terminal acquisition module, a core algorithm module, and a user interaction module. These modules work together to effectively manage the identities of bid evaluation meeting participants and accurately enter their personal information.

[0020] The terminal acquisition module is responsible for identifying the identity of meeting participants and integrating the various data obtained to form identification data. It includes a facial recognition unit, a QR code scanning unit, and an ID card reader unit, which use various technical means to obtain participant identity information. The facial recognition unit performs facial recognition based on a strong classifier composed of multiple weak classifiers. Weak classifiers can be classifiers that determine simple image features, such as the presence of edges in a specific direction or regions of a specific shape. Multiple weak classifiers are combined in a specific manner (such as the AdaBoost algorithm) to form a strong classifier. The strong classifier comprehensively considers the judgment results of multiple weak classifiers, improving the accuracy and robustness of facial recognition. Specifically, when a participant enters the recognition range of the portable bid evaluation meeting site management device, the facial recognition unit first captures the participant's facial image. The facial image is then input into the strong classifier composed of multiple weak classifiers to extract and analyze features, ultimately obtaining facial feature recognition data such as facial contour, facial feature location, and shape.

[0021] The QR code scanning unit is based on the quick response matrix code for recognition. The quick response matrix code is a graphic code that can store a large amount of information. It converts the information into a combination of black and white modules through specific coding rules. The QR code scanning unit uses image acquisition and recognition algorithms to read the information in the quick response matrix code. Specifically, participants can present a QR code containing personal identity information, and the QR code scanning unit uses a camera to capture the QR code image. After pre-processing the QR code image (such as grayscale, binarization, denoising, etc.), the position and direction of the quick response matrix code are located, and then the data module in the quick response matrix code is extracted, and decoding and error correction processing are performed to finally obtain the QR code information recognition data.

[0022] The ID card reader unit uses a built-in RFID radio frequency component to identify ID cards. ID cards contain a built-in RFID chip that stores a citizen's identity information. The RFID component in the ID card reader unit communicates with the ID card chip via wireless communication, reading the information stored in the chip and obtaining the ID card's identification data, such as name, gender, and ID number.

[0023] Ultimately, facial feature recognition data, QR code information recognition data, and ID card information recognition data can be used together as recognition data to provide data support for subsequent core algorithm modules.

[0024] Next, the core algorithm module analyzes the identification data obtained by the terminal acquisition module to determine whether the identity of the participants matches the current bid evaluation meeting, and groups the matched participants according to the preset bid evaluation personnel categories to obtain the grouping results. Specifically, the core algorithm module first compares the identification data with the pre-stored list of participants in the bid evaluation meeting. If the identification data successfully matches a record in the list, the identity of the participant is considered to match the current bid evaluation meeting; otherwise, the participant is considered to be unmatched and cannot enter the bid evaluation meeting site or further verification is required. For participants whose identities are successfully matched, the core algorithm module groups them according to the preset bid evaluation personnel categories corresponding to the current bid evaluation meeting. The preset bid evaluation personnel categories may include bid evaluation experts, tenderer representatives, supervisors, etc. The grouping rules can be set according to factors such as the identity information, professional fields, and roles of the participants.

[0025] The user interaction module generates a corresponding information entry interface based on the grouping results obtained by the core algorithm module. It provides users with an interface for interacting with the device, making it convenient for participants to complete information entry operations. The interface can display the participant's group information and the personal information fields that need to be entered, such as contact information and work unit. The information entry interface can be displayed on the display screen of the portable bid evaluation meeting on-site management device. The interface design should be simple and clear to facilitate participant operation. Participants can enter their personal information according to the prompts on the information entry interface. The user interaction module receives the information entered by the participant and performs format verification and error prompts. For example, it checks whether the mobile phone number format is correct and prompts the participant to re-enter if the format is incorrect. After entry is completed, the user interaction module associates the personal information entered by the participant with the identification data and stores it for subsequent meeting management and data analysis.

[0026] By applying the technical solution of this embodiment, the terminal acquisition module is responsible for identifying the identity information of the participants and integrating the various data obtained by identification to form identification data. It includes a face recognition unit, a QR code scanning unit and an ID card reading unit to obtain identity-related information of the participants through different technical means. Ultimately, the facial feature recognition data output by the face recognition unit, the QR code information recognition data output by the QR code scanning unit and the ID card information recognition data output by the ID card reading unit can be used together as identification data to provide data support for the subsequent core algorithm module. The core algorithm module then analyzes the identification data obtained by the terminal acquisition module to determine whether the identity of the participant matches the current bid evaluation meeting, and groups the matched participants according to the preset bid evaluation personnel categories to obtain grouping results. The user interaction module generates a corresponding information entry interface based on the grouping results obtained by the core algorithm module. The interface can display the group information of the participants and the personal information fields that need to be entered. The embodiment of the present application improves the accuracy and reliability of identity recognition by combining three methods: face recognition, QR code scanning and ID card reading, and can effectively prevent violations such as impersonation; the core algorithm module can automatically group participants according to the preset evaluator categories corresponding to each bid evaluation meeting, thereby improving the efficiency, accuracy and flexibility of meeting management; the portable bid evaluation meeting site management equipment adopts a portable design, which is convenient for deployment and use at different bid evaluation meeting sites, reducing the cost and difficulty of meeting organization.

[0027] In an embodiment of the present application, optionally, the core algorithm module is specifically used to: classify the facial feature recognition data based on a geometric classification method to determine the first identity information of the participant; analyze the QR code information recognition data and the ID card information recognition data based on a selection tree algorithm to determine the second identity information of the participant; when the first identity information matches the second identity information, determine that the identity authentication of the participant is passed, and filter out the participants who match the current bid evaluation meeting from the participants who have passed the identity authentication, obtain the professional information corresponding to the matched participants, and based on the professional information, group the matched participants according to the preset bid evaluation personnel categories corresponding to the current bid evaluation meeting through a dynamic clustering algorithm to obtain the grouping results.

[0028] In this embodiment, the core algorithm module plays a key role in data processing and decision-making within the portable bid evaluation meeting site management device. It uses various algorithms to analyze and process facial recognition data, QR code information, and ID card information acquired by the terminal acquisition module to determine whether participants' identities match. It then groups participants based on their professional expertise, providing accurate personnel classification information to ensure smooth meetings.

[0029] The core algorithm module can determine the primary identity information of each participant based on geometric classification. Geometric classification is a classification method based on the geometric relationships of facial features. It primarily utilizes geometric features such as the relative position, distance, and angle between facial organs (such as the eyes, nose, and mouth) for identity recognition and classification. These geometric features are relatively stable and are not significantly affected by factors such as lighting and facial expression. Specifically, key geometric features are first extracted from the facial feature recognition data. For example, the distance between the eyes, the vertical distance between the eyes and nose, and the horizontal distance between the nose tip and mouth are measured. These features can be represented numerically to form a feature vector. Next, the extracted geometric feature vector of the participant's face is input into a classification model, which classifies the feature vector based on learned patterns to determine the participant's primary identity information. The primary identity information is a preliminary identity determination result derived from the facial feature recognition data. The classification model can be a pre-built geometric feature-based classification model. This model is obtained by learning and training the facial geometric features of a large number of individuals with known identities. During the training process, the model learns the distribution patterns and differences in the facial geometric features of individuals with different identities.

[0030] The core algorithm module can also determine the attendee's secondary identity information based on a selection tree algorithm. This algorithm is a classification algorithm based on a decision tree. It classifies data by constructing a tree structure. Each node in the tree represents a test on an attribute, branches represent test outputs, and leaf nodes represent categories or values. When processing QR code and ID card identification data, the selection tree algorithm can make step-by-step judgments based on the different attributes in the data to ultimately determine the attendee's secondary identity information. Specifically, the QR code and ID card identification data are preprocessed to extract key attributes. For example, attributes such as name, ID number, and gender are extracted from the ID card information; attributes such as identity identifiers and role information that may be included in the QR code information are extracted from the QR code information. The preprocessed data is then input into the selection tree, which is traversed downwards according to the selection tree's judgment logic until a leaf node is reached, thereby determining the attendee's secondary identity information. The secondary identity information is the identity judgment result derived from the QR code and ID card information. The selection tree can be pre-constructed based on historical data and business rules. The selection tree construction process includes selecting the optimal attributes as the root node and internal nodes, and determining the attribute partitioning thresholds. For example, you can make a preliminary judgment based on the ID number, because the ID number is unique and can quickly screen out some participants.

[0031] The core algorithm module also performs identity matching and verification. Specifically, it compares the first identity information obtained using the geometric classification method with the second identity information obtained using the selection tree algorithm. If the two match, the participant's identity information has been verified across multiple dimensions, including facial features, QR code, and ID card, and authentication has been successful. If the two do not match, there may be an identity anomaly, requiring further verification or denying the participant entry.

[0032] When the first identity information matches the second identity information, it is determined that the participant's identity verification has passed. Next, the list of participants for the current bid evaluation meeting is obtained, and the participants who have passed the identity verification are further screened based on the list of participants. The screened participants are used as the participants matching the current bid evaluation meeting. Subsequently, the professional information corresponding to the matched participants is obtained. Professional information can be pre-stored in a database and associated with identity information. For example, information such as the participant's professional field, skill level, etc. can be queried from the database using the ID number or a specific identity identifier. Furthermore, the obtained professional information of the participants (such as professional field, skill level, work experience, etc.) is quantified to form a data vector that can be used for clustering. The pre-processed data vector is input into a dynamic clustering algorithm. The dynamic clustering algorithm performs initial clustering based on the similarity between the data (such as the correlation between professional fields, the matching degree of skill levels, etc.), and then continuously adjusts the clustering results through iterative optimization until the optimal grouping effect is achieved. A dynamic clustering algorithm is an algorithm that can automatically adjust the clustering results according to the dynamic changes of the data. It does not require a predetermined number of clusters, but instead automatically divides data into different groups based on similarities. During the grouping process, the algorithm continuously adjusts cluster centers and group boundaries to adapt to the data distribution characteristics. Based on the results of the dynamic clustering algorithm, participants are grouped according to pre-set evaluator categories corresponding to the current bid evaluation meeting. Pre-set evaluator categories can include expert groups in different professional fields, tenderer representatives, supervisors, and other groups. The grouping results can be output to the user interaction module for participants to review and confirm.

[0033] The embodiment of the present application uses multiple algorithms combined with multiple data sources to perform identity authentication, greatly reducing the risk of identity fraud; using a dynamic clustering algorithm to automatically group according to professional information, avoiding the tediousness and subjectivity of manual grouping, and improving the efficiency of meeting management.

[0034] In an embodiment of the present application, optionally, the face recognition unit is specifically used to: collect face images of the participants and call each pre-trained weak classifier; for each weak classifier, divide the face image based on the weak classifier to obtain multiple target areas, perform feature extraction on each target area in the face image in turn through the weak classifier to obtain a feature extraction result corresponding to each target area, and judge whether the target area belongs to the face area based on the feature extraction result corresponding to each target area and a preset face classification rule to obtain a judgment result; for each target area, the strong classifier calculates a reliability value of whether the target area belongs to the face area based on the judgment results of each weak classifier on the target area and the weight pre-assigned to each weak classifier, and identifies whether the target area belongs to the face area based on the reliability value to obtain a face recognition result; the strong classifier marks the final face area from the face image based on the face recognition results corresponding to each target area, and performs feature extraction on the final face area according to the preset geometric feature extraction rule and / or the preset texture feature extraction rule to obtain facial feature recognition data.

[0035] In this embodiment, the facial recognition unit uses a camera or other image acquisition device to capture facial images of meeting participants. The camera must have sufficient resolution and frame rate to clearly capture facial details. The captured facial images may be affected by factors such as lighting, angle, and occlusion. Therefore, preprocessing operations such as grayscale conversion, denoising, and histogram equalization can be performed to improve image quality and prepare for subsequent processing.

[0036] A number of weak classifiers are pre-trained in the face recognition unit. These weak classifiers are constructed based on simple features (such as edge detection, texture analysis, etc.), and each weak classifier is responsible for identifying specific features or patterns in the image. Specifically, for the collected face image, each weak classifier divides the face image into multiple target areas according to its specific division strategy. The division strategy can be a uniform grid division or an uneven division based on certain prior knowledge. The division strategies set by different weak classifiers are the same, so the areas divided by different weak classifiers are the same. Each target area is a sub-area in the face image, and the weak classifier can independently analyze and judge these sub-areas to determine whether the area belongs to the face area.

[0037] Next, each weak classifier extracts features from the target area it is responsible for. Feature extraction methods can include edge detection, texture analysis, color distribution, etc. For example, one weak classifier can focus on detecting horizontal edges in an image, while another can focus on detecting vertical edges. Subsequently, according to preset face classification rules, each weak classifier analyzes the extracted features to determine whether the target area belongs to a face. The preset face classification rules can be based on threshold judgments, such as if the intensity of a feature exceeds a certain threshold, it is considered to belong to the face area.

[0038] Each weak classifier is assigned a weight during the training phase, and the size of the weight reflects the importance of the weak classifier in the entire classification process. For example, a weak classifier with better performance can be assigned a higher weight. For each target area, the strong classifier collects the judgment results of all weak classifiers on the area (belongs to or does not belong to the face area), and combines the weights of each weak classifier to calculate the reliability value of the target area belonging to the face area. The calculation of the reliability value can be a weighted summation or other comprehensive methods. Afterwards, based on the calculated reliability value, the strong classifier determines whether the target area belongs to the face area. If the reliability value exceeds the preset threshold, the area is considered to belong to the face area; otherwise, it is considered not to belong. After the strong classifier judges all target areas, it generates a face recognition result, that is, which areas are identified as face areas. Through this method, the single-point positioning accuracy can be achieved to 0.25nm.

[0039] Furthermore, based on the face recognition results for each target region, the strong classifier merges adjacent or overlapping face regions to form a complete final face region. This can be achieved through methods such as region growing and connected component analysis. Furthermore, the finalized face region can be marked on the original face image.

[0040] Then facial feature extraction is performed. Specifically, according to the preset geometric feature extraction rules and / or texture feature extraction rules, detailed feature extraction is performed on the final area of ​​the marked face. Geometric features: including the position, shape, size of facial organs (such as eyes, nose, mouth) and their geometric relationship with each other (such as the distance between the two eyes, the vertical distance between the nose and the mouth, etc.). Texture features: including detailed features such as skin texture, wrinkles, spots, etc., which can be extracted through methods such as local binary pattern (LBP) and gray level co-occurrence matrix (GLCM). Finally, the extracted geometric features and / or texture features are integrated and encoded to generate facial feature recognition data.

[0041] The embodiments of the present application can effectively improve the accuracy of face recognition and reduce false positives and missed judgments through the collaborative work of multiple weak classifiers and the comprehensive judgment of strong classifiers; can adapt to the face recognition needs under complex scenes such as different lighting, angles, and occlusions, and have good robustness; combined with the extraction of geometric features and texture features, it can more comprehensively describe the characteristic information of the face.

[0042] In an embodiment of the present application, optionally, the QR code scanning unit is specifically used to: collect the QR code image of the participant, and extract the target QR code from the QR code image based on the position detection image, wherein the target QR code is generated based on the quick response matrix code; parse the target QR code to obtain the quick response matrix code, and determine the data block and error correction code block from the quick response matrix code; convert the data block into a binary code, and use the error correction code block to perform error correction processing on the binary code to obtain QR code information identification data.

[0043] In this embodiment, the QR code scanning unit can be equipped with an image acquisition device such as a camera, capable of capturing images of QR codes presented by participants. The acquisition process may be affected by factors such as lighting, angle, and distance. Therefore, the captured image can undergo certain preprocessing steps, such as brightness adjustment and contrast enhancement, to improve image quality. Next, the captured QR code image is searched for a location detection image. By identifying features in the location detection image, the position, orientation, and size of the target QR code within the QR code image are determined. The location detection image serves as a reference for QR code positioning and correction. Based on this information, the target QR code region is extracted from the original image, and background and other interference information are removed to obtain an image containing only the target QR code content. The QR code scanning unit then uses a specific parsing algorithm to parse the extracted target QR code. The parsing algorithm decodes the modules within the target QR code based on the QR code's encoding rules and format information. After parsing, a complete Quick Response matrix code (QRC) is obtained. This matrix code consists of a series of black and white modules that contain the encoded data information. The Quick Response Matrix Code is compatible with digital, alphabetic, and Chinese character encodings, parsing it in ≤1 second with 100% accuracy. The Quick Response Matrix Code consists of a data area and an error correction code area. The data area stores the actual data to be transmitted, while the error correction code area stores the error correction code used to correct data errors. Therefore, the QR code scanning unit can separate the data block and error correction code block from the Quick Response Matrix Code according to the QR code format specifications. The data block contains information such as the identity of the participants and meeting information, while the error correction code block is used to recover potentially damaged data during subsequent error correction processing. The data in the QR code is stored in a specific encoding method, such as digital encoding, alphanumeric encoding, or byte encoding. The QR code scanning unit converts each character or data unit in the data block into its corresponding binary code according to the QR code encoding rules. Specifically, each element in the data block can be converted into a binary representation according to the encoding rules' mapping table, resulting in a complete binary code sequence.

[0044] In addition, the error correction code stored in the error correction code block is generated based on a certain error correction algorithm (such as Reed-Solomon code). When errors occur in the data during transmission or storage, the error correction code can detect and correct these errors through a specific algorithm. Therefore, the QR code scanning unit compares and analyzes the converted binary code with the error correction code in the error correction code block. The error correction algorithm is used to detect whether there are errors in the binary code, and the erroneous data is corrected based on the information in the error correction code. After the error correction process, accurate QR code information recognition data is obtained, which can be further used for operations such as identity authentication and information storage.

[0045] The embodiment of the present application can effectively improve the accuracy of QR code recognition and reduce recognition errors caused by factors such as image quality and interference through the positioning of position detection images and error correction processing of error correction code blocks; the parsing and processing algorithms of the QR code scanning unit have been optimized and can complete the collection, parsing and error correction processing of QR codes in a short time, thereby realizing rapid identity recognition and information acquisition.

[0046] In an embodiment of the present application, optionally, the ID card reading unit is specifically used to: establish a wireless communication connection with the ID card built-in chip of the participant based on the built-in RFID radio frequency component, and send an identity authentication request to the ID card built-in chip after the connection, so that the ID card built-in chip verifies whether the identity authentication request is legal; receive feedback information sent by the ID card built-in chip indicating that the identity authentication request is a legal request, and send a data reading instruction to the ID card built-in chip; receive binary data returned by the ID card built-in chip based on the data reading instruction, and parse the binary data to obtain ID card information identification data.

[0047] In this embodiment, when a participant brings his or her ID card close to the ID card reading unit, the RFID radio frequency component of the ID card reading unit can actively transmit a radio frequency signal. After receiving the signal, the built-in chip in the ID card can respond, thereby establishing a wireless communication connection between the ID card reading unit and the built-in chip in the ID card. This connection is based on wireless transmission of radio frequency signals, does not require physical contact, and is convenient and fast. Among them, RFID (Radio Frequency Identification) is a radio frequency identification technology that automatically identifies the target object through radio frequency signals and obtains relevant data. The RFID radio frequency component built into the ID card reading unit is capable of transmitting and receiving radio frequency signals of a specific frequency. The time to read data from the built-in chip in the ID card through the RFID radio frequency component is ≤1 second, and the success rate is over 99%.

[0048] After successfully establishing a connection, the ID card reader generates an authentication request. This request contains specific identification information and encryption parameters, indicating the identity and purpose of the request to the ID card's built-in chip. The ID card reader sends the authentication request to the ID card's built-in chip over the established wireless communication connection. This step allows the ID card's built-in chip to verify the legitimacy of the request, ensuring that only authorized devices can read ID card information, thus ensuring information security.

[0049] After receiving the identity verification request, the chip embedded in the ID card verifies it according to pre-set algorithms and rules. For example, the chip can check whether the identification information in the request matches a known legitimate device and whether the encryption parameters are correct. If the identity verification request is verified as legitimate, the chip embedded in the ID card can send a feedback message to the ID card reader indicating that the request is legitimate. This feedback message is usually a specific radio frequency signal containing relevant information indicating that the verification was successful.

[0050] The ID card reader receives feedback from the ID card's built-in chip via the RFID radio frequency component and parses the information to confirm that the identity verification request has been approved. The ID card reader then generates a data read instruction. This instruction specifies the type and range of data to be read from the ID card's built-in chip, such as basic information such as name, gender, ID number, and photo. The ID card reader again transmits the data read instruction to the ID card's built-in chip via wireless communication, informing the chip of the required data.

[0051] After receiving the data reading instruction, the chip built into the ID card extracts the corresponding data from its own storage area and converts it into binary format. It then sends the binary data back to the ID card reading unit via a wireless communication connection.

[0052] The RFID module in the ID card reader continuously receives binary data from the ID card's built-in chip and parses it bit by bit. For example, it interprets specific binary bit combinations as Chinese characters in a name or numbers in an ID card number. In this way, the binary data is converted into human-readable ID card information such as name, gender, ethnicity, date of birth, address, ID card number, and photo.

[0053] The embodiment of the present application verifies the legitimacy of the identity authentication request to ensure that only authorized devices can read the ID card information, effectively preventing the risk of illegal reading and information leakage; it uses RFID technology to achieve wireless communication connection, without the need to insert the ID card into the device or make physical contact, which is convenient and fast to operate and improves the user experience.

[0054] In an embodiment of the present application, optionally, the device also includes a data management module; the data management module is used to store the identity authentication results and grouping results of the participants, and, in response to a data export instruction, obtain the bid evaluation meeting corresponding to the data export instruction, identify the meeting type of the bid evaluation meeting, call the target template corresponding to the meeting type, and generate a bid evaluation meeting report based on the identity authentication results, the grouping results and the target template.

[0055] In this embodiment, before the bid evaluation meeting begins, the identity of the participants has been verified through the facial recognition unit, QR code scanning unit, and ID card reading unit. The data management module can receive the identity verification results from these units in real time, including information such as whether the verification is passed, the verification time, and the verification method (face, QR code, ID card). Then, the identity verification results are stored in a structured manner in the database. For example, a record is created for each participant, and the record contains fields such as name, ID card number (encrypted storage), verification pass status, and verification timestamp. This storage method facilitates subsequent queries and statistical analysis.

[0056] Furthermore, the data management module receives the grouping results from the core algorithm module and identifies the group to which each participant belongs. The module associates the grouping results with the identity verification results and stores them. For example, a "Group" field is added to the participant's database record to record the group to which the participant belongs. This allows for easy access to information about all participants in a given group during subsequent data processing.

[0057] When a user needs to export data related to a bid evaluation meeting, they can issue a data export command through the user interface or other interfaces. The data management module receives this command in real time and parses the relevant information in the command, such as the bid evaluation meeting identifier and export format. The data management module then searches the database for the corresponding bid evaluation meeting record based on the information contained in the command, including the bid evaluation meeting identifier, and identifies the meeting's detailed information, including the meeting time, location, and attendee list.

[0058] Different bid evaluation meetings can be of different types, such as technical review meetings, business review meetings, and comprehensive review meetings. Each type of meeting may have different requirements for data statistics and report formats. Therefore, the data management module can also extract meeting type information from the bid evaluation meeting records or automatically identify the meeting based on characteristics such as the meeting name and subject. For example, if the meeting name contains "technical review," the meeting is considered a technical review meeting. For different types of bid evaluation meetings, the corresponding target template is retrieved from pre-designed report templates. The stored authentication and grouping results are populated into the report's variable data area according to the target template's format requirements. For example, the report may list each participant's name, authentication status, group affiliation, and other information. After data is populated, the data management module generates the final bid evaluation meeting report according to the target template's formatting rules. The report can be formatted in common electronic document formats such as Excel and PDF. After the report is generated, it can be exported to an external storage device or sent to a designated email address, server, or other location via an output interface (such as a USB port or network interface) for easy subsequent use and sharing.

[0059] The embodiment of the present application stores the identity authentication results and grouping results of the participants in a data management module, which is convenient for unified management and query, and avoids the dispersion and loss of data; through the preset target template and automated data filling process, it can quickly generate bid evaluation meeting reports that meet the requirements, improve work efficiency, and reduce errors caused by manual operations; it can call corresponding target templates according to different bid evaluation meeting types to meet the personalized reporting needs of different meetings, thereby enhancing the flexibility and versatility of the system.

[0060] In an embodiment of the present application, optionally, the device also includes a hardware protection module, which meets the IP67 waterproof and dustproof standards, adapts to an ambient temperature of -10°C to 50°C, a humidity of 5% RH to 95% RH, and tolerates ±8KV electrostatic interference; the hardware protection module is also used to monitor the ambient temperature and ambient humidity of the bid evaluation meeting site based on a built-in temperature sensor and humidity sensor, and when it is monitored that the ambient temperature and / or ambient humidity of the bid evaluation meeting site exceed the set range, it automatically triggers an alarm and enters a protection mode.

[0061] In this embodiment, the hardware protection module provides protection for the portable bid evaluation meeting site management device. It not only offers excellent physical protection, meeting specific standards for water and dust resistance, temperature and humidity adaptability, and electrostatic interference tolerance, but also includes environmental monitoring and automatic protection capabilities. Built-in sensors monitor the environmental parameters of the bid evaluation meeting site in real time. When environmental conditions exceed the set range, timely alarms are issued and protective measures are implemented, ensuring stable operation of the device in various environments and guaranteeing the smooth progress of the bid evaluation meeting.

[0062] The IP (Ingress Protection) rating consists of two numbers: the first indicates the device's degree of protection against dust and foreign objects, and the second indicates its degree of sealing against moisture and water intrusion. For bid evaluation conference equipment, IP67 means that even in the event of accidental water splashing or relatively humid conditions at the conference site, the hardware protection module effectively protects the device's internal components from water damage. Furthermore, this hardware protection module enables the device to operate normally in ambient temperatures ranging from -10°C to 50°C, adapting to conference environments across different seasons and regions. Whether in cold winter indoor environments or hot summer meeting rooms, the portable bid evaluation conference site management device can operate stably, providing reliable support for bid evaluation meetings. Furthermore, the humidity range of 5% to 95% RH covers the humidity conditions of most conference venues. Whether in a dry air-conditioned room or a damp basement conference room, the hardware protection module effectively prevents the adverse effects of humidity and ensures normal operation. The hardware protection module is also resistant to electrostatic interference of ±8kV, effectively protecting the electronic components within the portable bid evaluation conference site management device from electrostatic discharge damage. This improves the reliability and stability of portable bid evaluation meeting on-site management equipment in electrostatic environments and reduces the risk of equipment failure due to electrostatic interference.

[0063] In addition, when the hardware protection module detects that the ambient temperature and / or ambient humidity are outside the set range, it can immediately send an alarm signal to the control system of the portable bid evaluation meeting site management device. The control system can issue an alarm through sound, light or screen display to remind the meeting organizer of abnormal environmental conditions. At the same time, the hardware protection module automatically enters protection mode. In protection mode, the portable bid evaluation meeting site management device can take some measures to protect itself, such as reducing the operating power of the equipment, suspending the operation of some non-critical functions, starting the heat dissipation or dehumidification device (if the equipment is equipped), etc., to prevent the environmental conditions from causing further damage to the equipment. When the environmental conditions return to normal, it automatically exits the protection mode and resumes normal operation.

[0064] The hardware protection module in the embodiment of the present application has excellent physical protection capabilities and environmental monitoring and automatic protection functions, and can operate stably under various harsh environmental conditions, reducing the risk of failure of portable bid evaluation meeting on-site management equipment and improving the reliability and stability of the bid evaluation meeting; by real-time monitoring of environmental parameters and timely issuing alarms and entering protection mode, it can effectively avoid environmental conditions from causing damage to portable bid evaluation meeting on-site management equipment, extend the service life of the equipment, and reduce maintenance costs.

[0065] In an embodiment of the present application, optionally, the device also includes an electronic signature module; the electronic signature module is used to respond to a document signing instruction, output the evaluation document corresponding to the current evaluation meeting, and start the signature collection function to realize the encrypted signing of the evaluation document based on the signature collection function; the electronic signature module is also used to send the encrypted and signed evaluation document to the cloud.

[0066] In this embodiment, during the bid evaluation meeting, when a document needs to be signed, for example, when a bid evaluation expert confirms and signs the bid evaluation result report, the meeting organizer or relevant operator can issue a document signing instruction through the operating interface of the portable bid evaluation meeting on-site management device. After receiving the instruction, the electronic signature module parses the instruction to determine the type, name, version and other relevant information of the bid evaluation document that needs to be signed. Based on the file information obtained by the analysis, the electronic signature module locates the corresponding bid evaluation file in the local storage of the portable bid evaluation meeting on-site management device or in a storage system connected to the portable bid evaluation meeting on-site management device. These bid evaluation files can be uploaded to the device in advance during the meeting preparation stage, or generated in real time during the meeting. After finding the bid evaluation file, the bid evaluation file is output in a suitable format to the display interface of the portable bid evaluation meeting on-site management device for the signatory to view and confirm. The output file format can be a common document format, such as PDF, Word, etc., to ensure that the signatory can clearly read the file content.

[0067] The electronic signature module supports multiple signature collection methods, such as handwritten signatures and digital certificate signatures. The module selects the appropriate signature collection method based on the configuration of the portable bid evaluation conference site management device and user needs. If handwritten signatures are used, the portable bid evaluation conference site management device provides a handwriting input area where the signer can use a stylus or finger to write their signature on the device's touchscreen. The electronic signature module captures signature stroke trajectory, pressure level, and other information in real time. If digital certificate signatures are used, the signer inserts a smart card or USB key containing the digital certificate into the device. The electronic signature module interacts with the digital certificate to obtain the signer's identity information and signing key. After the signature collection function is enabled, the module guides the signer through user interface prompts and voice prompts. For example, prompts such as "Please write your signature here" or "Please insert your digital certificate and confirm your signature" may be displayed on the screen.

[0068] For handwritten signatures, the electronic signature module digitizes the collected information, such as stroke trajectory and pressure, to generate image data of the handwritten signature, and then encrypts the image data. The encryption algorithm can use a symmetric encryption algorithm (such as AES) or an asymmetric encryption algorithm (such as RSA) to ensure the security of the signature information. If a digital certificate signature is used, the electronic signature module can use the signature key in the digital certificate to encrypt the hash value of the evaluation document to generate a digital signature. The hash value is calculated on the content of the evaluation document using a specific hash algorithm (such as SHA-256), which can ensure the integrity and non-tamperability of the document.

[0069] The encrypted signature information is then bound to the bid evaluation document, forming an encrypted file containing both the bid evaluation document content and the signature information. This allows subsequent file verification to confirm the signing and integrity of the document by decrypting the signature information and comparing it with the original document content. Furthermore, the encrypted and signed bid evaluation document can be sent to the cloud for storage, enabling secure file backup. This allows for even if the portable bid evaluation meeting site management device malfunctions, is lost, or is damaged, the cloud-stored files can still be preserved intact, preventing data loss.

[0070] This embodiment of the application digitizes and automates the signing of bid evaluation documents, reducing the printing, delivery, and storage of paper documents, significantly shortening the signing cycle, and improving the efficiency of bid evaluation meetings. Encryption technology protects signature information and bid evaluation documents, ensuring the authenticity, integrity, and non-repudiation of document signing. Furthermore, cloud storage provides data backup and security protection mechanisms, further ensuring the security of signed bid evaluation documents.

[0071] In an embodiment of the present application, optionally, the core algorithm module is compatible with the 5G communication protocol; the core algorithm module is also used to communicate with the remote video conferencing system based on the 5G communication protocol.

[0072] In this embodiment, in complex bid evaluation projects, multiple departments or institutions may need to participate. After the core algorithm module is connected to the remote video conferencing system, real-time data sharing between all parties can be achieved. For example, different departments can upload their own data and analysis results to the video conferencing system, and the core algorithm module integrates and analyzes these data, and feeds back the analysis results to all parties in real time. Personnel from all parties can conduct collaborative discussions and decision-making through the video conferencing system, improving work efficiency and the scientific nature of decision-making. After the core algorithm module is compatible with the 5G communication protocol, these data can be transmitted at a faster speed, reducing data transmission time, enabling the core algorithm module to obtain the required data and output results faster. For bid evaluation meeting scenarios that require real-time interaction, such as remote experts participating in discussions and decision-making in real time, the core algorithm module communicates with the remote system through the 5G network, which can ensure real-time transmission of information, enabling all parties to obtain the latest algorithm analysis results and meeting progress in a timely manner, improving the efficiency of the meeting and the accuracy of decision-making.

[0073] The embodiment of the present application is compatible with the 5G communication protocol and connected to the remote video conferencing system, thereby achieving efficient collaboration between the core algorithm module and remote personnel. Experts and decision makers, both local and remote, can participate in the bid evaluation meeting. All parties can share data and information in real time, communicate and make decisions in a timely manner, greatly shortening the bid evaluation project cycle. At the same time, it can provide more comprehensive and accurate information support for bid evaluation decisions, thereby improving the scientificity and rationality of decision-making.

[0074] In an embodiment of the present application, optionally, data is transmitted between the terminal acquisition module and the core algorithm module via an encrypted communication protocol.

[0075] In this embodiment, the encrypted communication protocol typically includes an identity verification mechanism to ensure that both communicating parties between the terminal acquisition module and the core algorithm module are legitimate devices or systems. This prevents malicious devices from impersonating legitimate devices to access the system, ensuring the reliability of the entire system.

[0076] Furthermore, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, a method for using a portable bidding evaluation meeting on-site management device is provided, such as Figure 2 As shown, the method includes:

[0077] When the bid evaluation experts arrive at the bid evaluation meeting, they first use the facial recognition unit in the PDA (Personal Digital Assistant, i.e., the portable bid evaluation meeting site management device in this application) to perform facial recognition on the participants based on a strong classifier composed of multiple weak classifiers, obtaining facial feature recognition data. Next, the QR code scanning unit therein scans the participant's QR code based on a quick response matrix code to obtain QR code information recognition data. Furthermore, the ID card reading unit therein can also recognize the participant's identification document to obtain ID card information recognition data. Subsequently, the core algorithm module analyzes the facial feature recognition data, QR code information recognition data, and ID card information recognition data, ultimately outputting a grouping result for the participants matching the current bid evaluation meeting and determining the participant's lounge, meeting room information, etc. based on the grouping result. The user interaction module can generate an information display interface (i.e., the aforementioned information entry interface) containing this information for the experts to view. Furthermore, the experts can also enter personal information through the information display interface to supplement the expert information. This personal information can include, for example, a bank card number. Furthermore, the personal information entered by the experts can be stored in a database for subsequent use. It should be noted that identity verification based on identification data can be implemented through a database. Specifically, an identity verification request can be sent to the database, which can then query the database and return a verification result. The database can pre-store the identity information of each expert (such as their identification number).

[0078] In addition, administrators can also maintain expert information through the management page. For example, they can import basic expert information through the management page and save it in the database to facilitate subsequent verification of participant ID information through the database. Administrators can also export expert information through the management page.

[0079] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0080] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A portable bidding meeting site management device, characterized in that: Including terminal acquisition module, core algorithm module and user interaction module; The terminal acquisition module is used to identify the identity information of the participants and obtain identification data, wherein the terminal acquisition module includes a face recognition unit, a QR code scanning unit and an ID card reading unit; the face recognition unit is used to perform face recognition on the participant based on a strong classifier composed of multiple weak classifiers to obtain facial feature recognition data; the QR code scanning unit is used to identify the QR code of the participant based on a quick response matrix code to obtain QR code information recognition data; the ID card reading unit is used to identify the identification document of the participant based on a built-in RFID radio frequency component to obtain ID card information recognition data; the recognition data includes the facial feature recognition data, QR code information recognition data and ID card information recognition data; The core algorithm module is used to analyze the identification data, determine participants whose identities match the current bid evaluation meeting based on the analysis results, and group the matched participants according to preset bid evaluation personnel categories corresponding to the current bid evaluation meeting to obtain grouping results; The user interaction module is used to output an information entry interface including the grouping results, so that the participants can input personal information based on the information entry interface.

2. The device according to claim 1, characterized in that The core algorithm module is specifically used for: Classifying the facial feature recognition data based on a geometric classification method to determine the first identity information of the conference participant; Analyze the QR code information identification data and the ID card information identification data based on a selection tree algorithm to determine the second identity information of the participant; When the first identity information matches the second identity information, it is determined that the identity authentication of the participant has passed, and the participants who match the current bid evaluation meeting are screened out from the participants who have passed the identity authentication, and the professional information corresponding to the matched participants is obtained. Based on the professional information, the matched participants are grouped according to the preset bid evaluation personnel categories corresponding to the current bid evaluation meeting through a dynamic clustering algorithm to obtain the grouping results.

3. The device according to claim 1, characterized in that The face recognition unit is specifically used to: Collecting facial images of the participants and calling pre-trained weak classifiers; For each weak classifier, dividing the face image based on the weak classifier to obtain a plurality of target regions, sequentially performing feature extraction on each target region in the face image using the weak classifier to obtain a feature extraction result corresponding to each target region, and determining whether the target region is a face region based on the feature extraction result corresponding to each target region and a preset face classification rule to obtain a determination result; For each target area, the strong classifier calculates a reliability value of whether the target area belongs to a face area based on the judgment results of each weak classifier on the target area and the weights pre-assigned to each weak classifier, and identifies whether the target area belongs to a face area based on the reliability value to obtain a face recognition result; The strong classifier marks the final face area from the face image according to the face recognition results corresponding to each target area, and extracts features from the final face area according to preset geometric feature extraction rules and / or preset texture feature extraction rules to obtain facial feature recognition data.

4. The device according to claim 1, characterized in that The two-dimensional code scanning unit is specifically used for: Collecting a QR code image of the participant, and extracting a target QR code from the QR code image based on the position detection image, wherein the target QR code is generated based on a quick response matrix code; Parsing the target two-dimensional code to obtain the quick response matrix code, and determining a data block and an error correction code block from the quick response matrix code; The data block is converted into a binary code, and the error correction code block is used to perform error correction processing on the binary code to obtain two-dimensional code information recognition data.

5. The device according to claim 1, characterized in that The ID card reading unit is specifically used for: Based on the built-in RFID radio frequency component, a wireless communication connection is established between the built-in chip of the ID card of the participant, and after the connection is established, an identity authentication request is sent to the built-in chip of the ID card, so that the built-in chip of the ID card verifies whether the identity authentication request is legal; receiving feedback information sent by the chip built into the ID card indicating that the identity authentication request is a legitimate request, and sending a data reading instruction to the chip built into the ID card; Receive the binary data returned by the ID card built-in chip based on the data reading instruction, and parse the binary data to obtain ID card information identification data.

6. The device according to claim 1, characterized in that The device also includes a data management module; The data management module is used to store the identity authentication results and grouping results of the participants, and, in response to a data export instruction, obtain the bid evaluation meeting corresponding to the data export instruction, identify the meeting type of the bid evaluation meeting, call the target template corresponding to the meeting type, and generate a bid evaluation meeting report based on the identity authentication results, the grouping results and the target template.

7. The device according to claim 1, characterized in that The device also includes a hardware protection module that meets the IP67 waterproof and dustproof standard, adapts to an ambient temperature of -10°C to 50°C, a humidity of 5% RH to 95% RH, and withstands ±8KV electrostatic interference; The hardware protection module is also used to monitor the ambient temperature and humidity at the bid evaluation meeting site based on the built-in temperature sensor and humidity sensor, and automatically trigger an alarm and enter protection mode when the ambient temperature and / or humidity at the bid evaluation meeting site are detected to be outside the set range.

8. The device according to claim 1, characterized in that The device also includes an electronic signature module; The electronic signature module is configured to output the bid evaluation document corresponding to the current bid evaluation meeting in response to a document signing instruction, and to enable a signature collection function to implement encrypted signing of the bid evaluation document based on the signature collection function; The electronic signature module is also used to send the encrypted and signed evaluation documents to the cloud.

9. The device according to claim 1, characterized in that The core algorithm module is compatible with the 5G communication protocol; The core algorithm module is also used to communicate with the remote video conferencing system based on the 5G communication protocol.

10. The device according to claim 1, characterized in that Data is transmitted between the terminal acquisition module and the core algorithm module via an encrypted communication protocol.

Images