Examination room arrangement method and device, electronic equipment and program product

Abstract

The invention relates to an examination room arrangement method and device, electronic equipment and a program product. The examination room arrangement method comprises the steps that examinee information of multiple examinees to be arranged is acquired, and the examinee information comprises identification information; mapping the identification information into a first feature vector representing examinee group association degree features; determining a plurality of first reference vectors corresponding to the preset examination room; and allocating the plurality of examinees to be arranged to corresponding examination rooms at least according to a first feature space distance, the first feature space distance being a space distance between the first feature vector and the first reference vector. According to the examination room arrangement solver, the cheating prevention possibility is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer application technology, and in particular to an examination room arrangement method and device, electronic equipment and program products. Background Art

[0002] Examination is an important evaluation method in the field of education. Reasonable examination room arrangement is of great significance to maintaining examination fairness and preventing cheating. In the prior art, examination room arrangement is usually carried out in the order of student numbers or randomly assigned. However, these simple arrangement methods do not take cheating prevention into consideration or are insufficient in preventing cheating.

[0003] Therefore, it is hoped that an improved examination room arrangement solution can be provided.

[0004] The content of this background technology description is only for facilitating understanding of the relevant technology in this field and is not regarded as an admission of the prior art. Summary of the invention

[0005] The embodiment of the present invention aims to provide a solution for arranging an examination room, thereby effectively improving the possibility of preventing cheating through the arrangement of the examination room.

[0006] In a first aspect, an embodiment of the present invention provides a method for arranging an examination room, comprising:

[0007] Acquire candidate information of a plurality of candidates to be scheduled, wherein the candidate information includes identification information;

[0008] Mapping the identification information into a first feature vector representing the correlation characteristics of the examinee group;

[0009] Determining a plurality of first reference vectors corresponding to a preset examination room; and

[0010] The plurality of candidates to be scheduled are allocated to corresponding examination rooms at least according to a first feature space distance, wherein the first feature space distance is a space distance between the first feature vector and the first reference vector.

[0011] In some embodiments, allocating the plurality of candidates to be scheduled to corresponding examination rooms at least according to the first feature space distance includes:

[0012] Determine a first feature space distance between a first reference vector of each examination room and first feature vectors of at least some of the examinees to be arranged;

[0013] For each examination room, the set of candidates corresponding to the examination room is determined according to the order of the first feature space distance from far to near; or, for each examination room, the candidates corresponding to the first feature space distance greater than a preset threshold are assigned to the set of candidates corresponding to the examination room.

[0014] In some embodiments, the candidate information also includes historical score information. In these embodiments, the step of allocating the plurality of candidates to be scheduled to corresponding examination rooms at least based on the first feature space distance includes:

[0015] According to the score range determined by the historical score information, the examination room is divided into a plurality of examination room groups, and a preliminary selection set corresponding to each examination room group is determined, wherein the historical scores of the examinees in the preliminary selection set of each examination room group are within the score range corresponding to the examination room group;

[0016] Determine a first feature space distance between a first reference vector of each examination room in each examination room group and a first feature vector of an examinee in the preliminary selection set;

[0017] For each examination room in each examination room group, determine the set of candidates corresponding to the examination room according to the order of the first feature space distance from far to near; or, for each examination room in each examination room group, assign the candidates corresponding to the first feature space distance greater than a preset threshold to the set of candidates corresponding to the examination room.

[0018] In some embodiments, the candidate information also includes historical performance information. In these embodiments, the method further includes: mapping the historical performance information into a second feature vector that characterizes the characteristics of the candidate's ability level; and determining a plurality of second reference vectors corresponding to the preset examination room. In these embodiments, at least according to the first feature space distance, the plurality of candidates to be scheduled are assigned to the corresponding examination room, including: according to the first feature space distance and the second feature space distance, the plurality of candidates to be scheduled are assigned to the corresponding examination room, wherein the second feature space distance is the space distance between the second feature vector and the second reference vector.

[0019] In some embodiments, allocating the plurality of candidates to be scheduled to corresponding examination rooms according to the first feature space distance and the second feature space distance includes:

[0020] Dividing the examination room into a plurality of examination room groups, wherein examination rooms in the same examination room group have different first reference vectors and the same second reference vector;

[0021] Determine a second feature space distance between a second reference vector of each examination room group and second feature vectors of at least some of the examinees to be arranged;

[0022] For each examination room group, determine the preliminary selection set corresponding to the examination room group according to the order of the second feature space distance from small to large; or, for each examination room group, assign the examinees corresponding to the second feature space distance less than a preset threshold to the preliminary selection set corresponding to the examination room group;

[0023] Determine a first feature space distance between a first reference vector of each examination room in each examination room group and a first feature vector of an examinee in the preliminary selection set;

[0024] For each examination room in each examination room group, the set of candidates corresponding to the examination room is determined in order from far to near; or, for each examination room in each examination room group, the candidates corresponding to the first feature space distance greater than a preset threshold are assigned to the set of candidates corresponding to the examination room.

[0025] In some embodiments, allocating the plurality of candidates to be scheduled to corresponding examination rooms according to the first feature space distance and the second feature space distance includes:

[0026] Dividing the examination room into a plurality of examination room groups, wherein examination rooms in the same examination room group have the same first reference vector and different second reference vectors;

[0027] Determine a first feature space distance between a first reference vector of each examination room group and first feature vectors of at least some of the examinees to be arranged;

[0028] For each examination room group, determine the preliminary selection set corresponding to the examination room group according to the order of the first feature space distance from far to near; or, for each examination room group, assign the examinees corresponding to the first feature space distance greater than a preset threshold to the preliminary selection set corresponding to the examination room group;

[0029] Determine a second feature space distance between a second reference vector of each examination room in each examination room group and a second feature vector of an examinee in the preliminary selection set;

[0030] For each examination room in each examination room group, the set of candidates corresponding to the examination room is determined according to the order of the second feature space distance from small to large; or, for each examination room in each examination room group, the candidates corresponding to the second feature space distance less than the preset threshold are assigned to the set of candidates corresponding to the examination room.

[0031] In some embodiments, allocating the plurality of candidates to be scheduled to corresponding examination rooms according to the first feature space distance and the second feature space distance includes:

[0032] Determine a first feature space distance between a first reference vector of each examination room and first feature vectors of at least some of the examinees to be arranged;

[0033] Determine a second feature space distance between a second reference vector of each examination room and a second feature vector of at least part of the examinees to be arranged;

[0034] Determining a weighted combined comprehensive feature space distance of each examination room according to a first weight coefficient of the first feature space distance and a second weight coefficient of the second feature space distance, wherein the first weight coefficient and the second weight coefficient are opposite in sign; and

[0035] For each examination room, the set of candidates corresponding to the examination room is determined according to the order of the size of the comprehensive feature space distance; or, for each examination room, the set of candidates corresponding to the examination room is determined according to the comparison result of the comprehensive feature space distance with a preset threshold.

[0036] In some embodiments, it is characterized in that the allocating the plurality of candidates to be scheduled to corresponding examination rooms at least according to the first feature space distance further comprises:

[0037] Detecting whether there are duplicated candidates in the set of candidates in each examination room;

[0038] Temporarily storing the duplicated candidates in the waiting list;

[0039] According to the first feature space distance and the remaining capacity of each examination room, the examinees in the candidate set are reallocated to the examination room with remaining capacity.

[0040] In some embodiments, the examination room arrangement method further includes:

[0041] Dynamically randomize seats for candidates assigned to each examination room, including:

[0042] Generate a random number seed based on the exam room number;

[0043] According to the random number seed, a hash operation is performed on the candidate number of each examination room to obtain a seat random vector; and

[0044] The seats of the examinees in each examination room are randomly sorted based on the seat random vector.

[0045] In some embodiments, the identification information includes student ID information, and mapping the identification information into a first feature vector representing a correlation feature of a group of examinees includes:

[0046] Based on the preset information extraction rules, the year information, class information, and serial number information are parsed from the student ID information;

[0047] Mapping the year information into a first characteristic component representing a time correlation;

[0048] Mapping the class information into a second feature component representing a degree of group association;

[0049] Mapping the serial number information into a third characteristic component representing individual distinction;

[0050] The first feature component, the second feature component and the third feature component are combined and processed to generate the first feature vector.

[0051] In some embodiments, the identification information includes school number and student number information. In these embodiments, mapping the identification information into a first feature vector representing the correlation characteristics of the examinee group includes:

[0052] Based on the preset information extraction rules, the school information is obtained from the school number, and the year information, class information, and serial number information are obtained from the student number information;

[0053] Mapping the year information into a first characteristic component representing a time correlation;

[0054] Mapping the class information into a second feature component representing a degree of group association;

[0055] Mapping the serial number information into a third characteristic component representing individual distinction;

[0056] Mapping the school information into a fourth characteristic component representing the degree of institutional relevance; and

[0057] The first feature component, the second feature component, the third feature component and the fourth feature component are combined and processed to generate the first feature vector.

[0058] In a second aspect, an embodiment of the present invention provides a test room arrangement device, comprising:

[0059] An acquisition unit, configured to acquire candidate information of a plurality of candidates to be scheduled, wherein the candidate information includes identification information;

[0060] A mapping unit, configured to map the identification information into a first feature vector representing a correlation feature of a group of examinees;

[0061] A reference unit configured to determine a plurality of first reference vectors corresponding to a preset examination room; and

[0062] an allocating unit, configured to allocate the plurality of candidates to be arranged to corresponding examination rooms at least according to a first feature space distance, wherein the first feature space distance is a space distance between the first feature vector and the first reference vector

[0063] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor and a memory storing a computer program, wherein the processor is configured to implement the method described in the first aspect when executing the computer program.

[0064] In a fourth aspect, an embodiment of the present invention provides a program product, comprising a computer program, wherein when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0065] In a fifth aspect, an embodiment of the present invention provides a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method described in the first aspect.

[0066] The embodiment of the present invention provides a method for arranging an examination room, which aims to solve various problems existing in the arrangement of examination rooms in the prior art. Specifically, in the method for arranging an examination room provided in the embodiment of the present invention, the candidate information of multiple candidates to be arranged can be obtained, and this information includes identification information (such as student number); these identification information are mapped into a first feature vector that characterizes the correlation characteristics of the candidate group; multiple first reference vectors corresponding to the preset examination room are determined; and multiple candidates to be arranged are assigned to the corresponding examination room at least according to the first feature space distance. Through the above-mentioned technical scheme of the embodiment of the present invention, the student number information can be converted into a computable feature vector, and the distance between the feature vectors can be used to measure the degree of correlation between candidates, so as to ensure that candidates with a long feature distance are assigned to the same examination room. This allocation method can maximize the heterogeneity of candidates in the examination room and reduce the proportion of familiar candidates, thereby reducing or solving the risk of interpersonal cheating caused by the familiar relationship that may exist between candidates.

[0067] In a further embodiment, on the basis of the above-mentioned examination room arrangement technical solution based on the long-distance allocation of the feature vector of the identifier (such as the student number), the historical score information is used as an additional reference factor to realize the examination room arrangement, thereby reducing or solving the risk of score-dependent cheating that may be caused by the large score gap between candidates in the examination room. In particular, a further embodiment of the present invention introduces a technical solution for examination room arrangement based on the multi-vector features of the identifier (such as the student number) and the historical scores, which not only considers the group association characteristics reflected by the student number, but also takes into account the ability level factors of the candidates, and realizes the balance of the score distribution of the candidates in the examination room.

[0068] In a further embodiment, on the basis of the above-mentioned examination room arrangement technical solution based on the remote allocation of the identification (such as student number) feature vector, a dynamic randomized seat allocation in the examination room is introduced, thereby reducing or solving the risk of cheating in advance due to the possibility that the examination room arrangement information or rules may be known in advance and lead to collusion in cheating. In a further embodiment of the present invention, through this dynamic randomization mechanism, the unpredictability of seat allocation in the examination room can be increased, and candidates are prevented from colluding in advance, thereby improving the fairness of the examination.

[0069] Other optional features and technical effects of the embodiments of the present invention are partially described below, and partially can be understood by reading this document. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The elements shown are not limited to the proportions shown in the accompanying drawings. The same or similar reference numerals in the accompanying drawings represent the same or similar elements, wherein:

[0071] Figure 1 is a first flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0072] Figure 2 is a second flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0073] Figure 3 is a third flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0074] Figure 4 is a fourth flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0075] Figure 5 is a fifth flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0076] Figure 6 is a sixth flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0077] Figure 7 is a seventh flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0078] Figure 8 is an eighth flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0079] Fig. 9 is a ninth flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0080] Fig.10 is a tenth flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0081] Fig.11 is an eleventh flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0082] Fig.12 is a twelfth flow chart of the examination room arrangement method according to an embodiment of the present invention;

[0083] Fig.13 is a module structure diagram of a test room arrangement device according to an embodiment of the present invention; and

[0084] Fig.14 An exemplary structural diagram of an electronic device capable of implementing the method according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0085] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific implementation methods and drawings. Here, the exemplary implementation methods of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0086] In the existing technology, the arrangement of examination rooms often has problems such as lack of randomness and easy prediction, which can easily lead to closely related candidates being assigned to adjacent positions, increasing the risk of cheating.

[0087] In this regard, this embodiment provides a method for arranging examination rooms based on vectorized calculation. The method for arranging examination rooms in the embodiment of the present invention achieves randomness and balance in the allocation of examinees by vectorizing examinee information and allocating it based on feature space distance, thereby effectively reducing or resolving the above-mentioned interpersonal relationship cheating risk.

[0088] like Figure 1 As shown, the examination room arrangement method of the embodiment of the present invention includes:

[0089] S110: Acquire candidate information of multiple candidates to be scheduled.

[0090] In some embodiments, the candidate information may include identification information.

[0091] In other embodiments, the candidate information may include student ID information and school number.

[0092] In some embodiments, the candidate information may also include other suitable information, such as historical performance information.

[0093] In some embodiments, the acquisition of candidate information can be achieved through database query, file import or API interface call. In a specific embodiment, for example, all candidate information that needs to take the exam can be obtained from the student management system, the examination management system or other data sources. For example, the system can obtain candidate information in batches from the examination database through SQL query. In this embodiment, the identification information can be the student number information of the candidate, such as a student number in the form of "20230142", where "2023" represents the year of admission, "01" represents the class (or other intermediate level) number, and "42" represents the student number (serial number). In a specific embodiment, the identification information can also include a school number, such as a school number in the form of "1001", which is used to identify the educational institution to which the candidate belongs.

[0094] Optionally, when obtaining the examinee information, the data can also be pre-processed, such as removing duplicate records, checking data integrity, unifying data formats, etc. This can ensure the quality of the data for subsequent processing and improve the accuracy of the examination room arrangement.

[0095] In other embodiments, while obtaining the examinee information, metadata such as the time and source of data acquisition can also be recorded, and this information can be used for subsequent auditing and tracing.

[0096] S120: Map the identification information into a first feature vector representing the correlation characteristics of the examinee group.

[0097] In the embodiment of the present invention, the acquired identification information may be mapped into feature vectors to achieve quantitative representation of the correlation between the examinee groups.

[0098] In some embodiments, a feature vector capable of characterizing the degree of association between examinees can be generated by extracting and converting the multi-dimensional information contained in the student ID.

[0099] In these embodiments, Figure 2 As shown, step S120 may include:

[0100] S121: Based on the preset information extraction rules, parse the student ID information to obtain the year information, class information and serial number information.

[0101] For example, for the student ID "20230142", the year information "2023", the class information "01" and the serial number information "42" can be parsed. These information reflect the characteristics of the examinee in the time dimension, group dimension and individual dimension respectively.

[0102] S122: Map the year information into a first characteristic component representing the time correlation.

[0103] S123: Mapping the class information into a second feature component representing the degree of group association.

[0104] S124: Map the serial number information into a third characteristic component representing individual distinguishability.

[0105] S125: The first feature component, the second feature component and the third feature component are combined and processed to generate a first feature vector.

[0106] In an embodiment of the present invention, the three feature components may be combined into a vector form, such as [2023, 01, 42], and standardized (such as normalized) processing may be performed during mapping or combination to ensure that the dimensions of the vectors are comparable. In some embodiments, the standardization (normalization) may be performed using methods such as maximum and minimum value normalization or Z-score normalization.

[0107] In a specific embodiment, the year information can be normalized during mapping, and the year information can be converted into a value relative to the base year. For example, if 2000 is taken as the base year, the time correlation of the 2023 grade can be expressed as 0.23, the 2022 grade as 0.22, and so on. This mapping method can reflect the degree of time correlation between examinees of different grades. In a specific embodiment, the class information can also be normalized. For example, the class number "01" can be mapped to the relative position value of the class among all classes, such as 0.01. This processing method can reflect the group correlation between examinees from the same or similar classes. In a specific embodiment, the serial number can also be normalized. For example, the serial number "42" is normalized to 0.42. This mapping method helps to distinguish different examinees in the same class.

[0108] Optionally, during the feature vector mapping process, different weights may be assigned to different feature components.

[0109] Accordingly, in step S140 described below, when determining the first feature space distance between the first feature vector and the first reference vector, it can include: A1: weighting the second feature component and the third feature component in the first feature vector, wherein the second feature component has an increased weight value and the third feature component has a decreased weight value; A2: calculating the first feature space distance between the weighted first feature vector and the first reference vector according to a preset distance algorithm.

[0110] In this embodiment, a larger weight can be assigned to the second feature component (class information), while a smaller weight can be assigned to the third feature component (serial number information). This weighted processing can better reflect the group correlation between examinees and facilitate the subsequent allocation of examination rooms. The first feature component corresponding to the grade information can have a weight between the weights of the second and third feature components. For example, the weights can be set to [0.3, 0.6, 0.1], respectively, so that class information occupies a more important position in the feature vector than grade information, and serial number information occupies a lower importance in the feature vector than grade information.

[0111] In some embodiments, data verification and exception processing can also be performed on the feature vector, for example, checking whether the feature components are within a reasonable range, processing missing or abnormal feature values, etc. This can ensure the quality and validity of the generated feature vector.

[0112] In other embodiments, the candidate information may also include a school number. In these embodiments, not only the candidate's student number information is processed, but also the school number information is combined to generate a feature vector containing the degree of institution association through the extraction and conversion of multi-dimensional information. At this time, the dimension of institution (school) association can be introduced into the process of generating the feature vector, so as to more comprehensively characterize the group association characteristics between candidates.

[0113] In these embodiments, Figure 3 As shown, step S120 may include:

[0114] S121': Based on the preset information extraction rules, the school information is parsed from the school number, and the year information, class information, and serial number information are parsed from the student number information. For example, for the school number "1001" and the student number "20230142", the school information "1001", the year information "2023", the class information "01", and the serial number information "42" can be parsed respectively.

[0115] S122': Map the year information into a first characteristic component representing the time correlation.

[0116] Similar to step S122, normalization processing may be used to convert the year information into a relative value between [0, 1].

[0117] S123': Map the class information into a second feature component representing the degree of group association.

[0118] Similar to step S123, normalization processing can be used to convert the class information into a numerical value reflecting the relationship between classes, such as mapping the class number "01" to 0.1.

[0119] S124': Map the serial number information to a third characteristic component representing individual distinction.

[0120] Similar to step S122, the serial number may be normalized by normalization processing, such as mapping "42" to 0.42.

[0121] S125': Map the school information into a fourth characteristic component representing the degree of institutional association.

[0122] In this embodiment, a characteristic component representing the degree of institutional association can be generated based on the numerical characteristics of the school number or a preset school mapping rule. For example, the school number "1001" can be mapped to 0.001, indicating the relative position of the school among all reference schools.

[0123] S126 ′: Combine the first feature component, the second feature component, the third feature component and the fourth feature component to generate a first feature vector.

[0124] Here, the four feature components can be combined into a vector form, such as [0.3, 0.1, 0.42, 0.001], which can be standardized during mapping or combination.

[0125] Also optionally, in the feature vector mapping process, different weights may be assigned to different feature components.

[0126] Accordingly, in step S140 described below, when determining the first feature space distance between the first feature vector and the first reference vector, it may include: B1: performing weighted processing on the second feature component, the third feature component and the fourth feature component in the first feature vector, wherein the second feature component and the fourth feature component have increased weight values ​​and the weight value of the fourth feature component is greater than the weight value of the second feature component, and the third feature component has a reduced weight value; B2: calculating the first feature space distance between the first feature vector and the reference vector after weighted processing according to a preset distance algorithm.

[0127] In this embodiment, the weights of the institution association degree (fourth characteristic component) and the second characteristic component (class information) can be set larger, and the institution association degree (fourth characteristic component) is greater than the second characteristic component (class information) to better distinguish candidates from different schools. The specific weight configuration can be [0.2, 0.3, 0.1, 0.4], so that school information plays a more important role in the characteristic vector.

[0128] In these embodiments, data verification and exception processing may also be performed on the feature vectors.

[0129] S130: Determine a plurality of first reference vectors corresponding to a preset examination room.

[0130] In some embodiments, a corresponding reference vector may be generated for each preset examination room according to the feature distribution of the first feature vector to achieve a reasonable allocation of examinees.

[0131] In a specific embodiment, the first feature vector distribution characteristics of all examinees can be determined, and based on these distribution characteristics, a suitable reference vector can be determined for each preset examination room. For example, for a three-dimensional feature vector containing year information, class information, and serial number information, the numerical distribution of each dimension can be statistically analyzed, including statistical characteristics such as mean and variance.

[0132] In a specific embodiment, the first reference vector can be determined based on a uniform division method of the feature distribution. In this specific example, assuming that there are N preset examination rooms, N first reference vectors can be set, and based on the uniform (or quasi-uniform) division method of the feature distribution, the feature space is evenly divided according to the number of examination rooms N, and the center point of each divided area is used as a reference vector. For example, for a three-dimensional feature vector, if the distribution range of the first feature component is [A, B], it can be divided into N equally spaced intervals, and the center value of each interval is used as the first component of the corresponding reference vector.

[0133] In another specific embodiment, the reference vector can be determined based on a clustering method. In this specific example, assuming that there are N preset examination rooms, N first reference vectors can be set accordingly, and based on the method of generating cluster centers, the feature vectors of all examinees can be clustered (such as K-means clustering, where K is equal to the number of preset examination rooms N), and the cluster center can be used as the reference vector. This method can better adapt to the actual distribution characteristics of the feature vector.

[0134] Optionally, when generating the reference vector, a random perturbation factor may be introduced to prevent the reference vector from being too regular. For example, a small random offset may be added to each component of the reference vector generated in the above manner to obtain the final reference vector, thereby increasing the unpredictability of the test center allocation.

[0135] In some embodiments, there may be multiple examination rooms corresponding to the same first reference vector, for example, when the examination rooms are grouped, as further described below. In these embodiments, assuming that there are N preset examination rooms, M first reference vectors may be set (M<N), and there may be multiple examination rooms corresponding to the same first reference vector.

[0136] In addition, the validity of the benchmark vectors can be verified. For example, the minimum distance between the benchmark vectors can be checked to see if it meets the preset threshold, ensuring that the benchmark vectors of different examination rooms have sufficient discrimination. For benchmark vectors that do not meet the requirements, they can be appropriately adjusted or regenerated.

[0137] S140: Allocate a plurality of candidates to be scheduled to corresponding examination rooms at least according to the first feature space distance.

[0138] In this embodiment, the first feature space distance is the space distance between the first feature vector and the first reference vector

[0139] In some embodiments, the examination room allocation of examinees can be achieved based on the spatial distance between the first feature vector and the first reference vector, and the first feature spatial distance reflects the degree of difference between the examinee's characteristics and the examination room reference characteristics.

[0140] In these embodiments, Figure 4 As shown, step S140 may include:

[0141] S141: Determine a first feature space distance between a first reference vector of each examination room and first feature vectors of at least some of the examinees to be arranged.

[0142] In the embodiment of the present invention, for each examination room, the first feature space distance between the first reference vector of the examination room and the first feature vectors of all or part of the arranged examinees can be determined respectively.

[0143] In some embodiments, for each examination room, the first feature space distance between the examination room and all the candidates to be scheduled can be determined. In this case, for example, the feature space distance calculation can be performed in parallel or traversally for multiple or even all examination rooms. Specifically, the first reference vector of each examination room can be traversed to calculate the space distance between it and the first feature vectors of all candidates to be scheduled.

[0144] In some embodiments, for at least some examination rooms, the first feature space distance between the examination room and some of the candidates to be scheduled can be determined. For example, the feature space distance calculation can be performed sequentially for each examination room, so that for the first examination room, the space distance between it and the first feature vector of all candidates to be scheduled can be calculated, and after determining the candidate set corresponding to the first examination room (step S142), the candidates included in the candidate set are removed from the candidates to be scheduled, and the same is true for other examination rooms.

[0145] In an embodiment of the present invention, any suitable distance algorithm may be used to calculate the distance between the candidate's feature vector and the reference vector, including but not limited to Euclidean distance, Manhattan distance, cosine distance, Chebyshev distance, Mahalanobis distance, and Minkowski distance.

[0146] In further embodiments, randomness may be introduced based on the distance calculation to further improve the unpredictability of the arrangement result. In some specific examples, a random vector perturbation may be introduced into the first feature space distance obtained by preliminary calculation or a random seed may be directly introduced when performing certain calculations, so that the final determined first feature space distance is random.

[0147] S142: For each examination room, determine the set of examinees corresponding to the examination room according to the order of first feature space distance from far to near; or, for each examination room, assign the examinees corresponding to the first feature space distance greater than a preset threshold to the set of examinees corresponding to the examination room.

[0148] In the embodiment of the present invention, the set of examinees corresponding to the examination room can be determined in a generally negative correlation with the first feature space distance. Thus, examinees who are far away from a certain examination room reference vector can be preferentially assigned to the examination room. This strategy helps to increase the differences between examinees.

[0149] In some embodiments, a sorting strategy may be adopted, that is, by sorting from far to near, so that candidates who are farther away from a certain examination room reference vector are preferentially assigned to the candidate set corresponding to the examination room. For example, if the spatial distance between candidate A and examination room A is 0.8, and the spatial distance between candidate B and examination room A is 0.3, candidate A is preferentially assigned to examination room A.

[0150] In other embodiments, a threshold comparison strategy may be adopted, that is, by comparing with a preset threshold, the examinees corresponding to the first feature space distance greater than the preset threshold are assigned to the examinee set corresponding to the examination room. For example, if the space distance threshold is set to 0.6, the space distance between examinee A and examination room A is 0.8, then examinee A is assigned to the examinee set corresponding to the examination room, and the space distance between examinee B and examination room A is 0.3, then examinee A is assigned to examination room A first.

[0151] In different embodiments, the number of examinees in the examination room set may be equal to, greater than, or less than the number of seats in the examination room, and the present invention is not limited thereto, and deduplication processing may be performed as required, as follows: Fig.10 shown.

[0152] In other embodiments, the historical score information of the examinee can also be considered when assigning the examinee. In these embodiments, the examinee information includes historical score information, and an assignment strategy of pre-grouping the examination room based on the score can be adopted to achieve a more sophisticated examination room arrangement.

[0153] In these embodiments, Figure 5 As shown, step S141 may include:

[0154] S141A: Divide the examination room into multiple examination room groups according to the score range determined by the historical score information, and determine the preliminary selection set corresponding to each examination room group.

[0155] In this embodiment, the historical scores of the examinees in the preliminary selection set of each examination room group are within the score range corresponding to the examination room group.

[0156] In the embodiment of the present invention, any suitable interval division method can be used to divide the intervals, such as dividing based on scores, dividing based on the number of examinees, or a combination of the two.

[0157] In the embodiment of the present invention, the numbers of examination rooms in different examination room groups may be equal (substantially equal), unequal or partially equal, which falls within the scope of the present invention.

[0158] In a specific embodiment, the historical score distribution characteristics of all candidates can be analyzed to set a scientific and reasonable score range. For example, the scores can be initially divided into several intervals, such as [90, 100], [80, 90), [70, 80), etc. Then, according to the proportion of candidates in each score range, the examination rooms are allocated to different examination room groups in the corresponding proportions; for example, there are N examination rooms in total, and candidates with historical scores in the interval of [90, 100] account for about 30% of the total number, then N*30% examination rooms (rounded up) can be allocated to the score interval.

[0159] In the embodiment of the present invention, for each score interval, examinees whose historical scores fall within the interval are classified into the preliminary selection set of the corresponding examination room group. The historical scores can be average scores or weighted scores.

[0160] S142A: Determine the first feature space distance between the first reference vector of each examination room in each examination room group and the first feature vector of the examinee in the preliminary selection set.

[0161] In these embodiments, after grouping, the spatial distance between the reference vector of each examination room in each examination room group and the feature vector of the examinees in the preliminary selection set of the group can be calculated. This process is performed separately for each examination room in each examination room group to ensure that the feature distance is calculated and compared within the same score level range.

[0162] In these embodiments, when calculating the spatial distance for each examination room of each group, it can be calculated with the feature vectors of all or part of the examinees in the preliminary selection set as needed. Similar features can refer to step S141, which will not be repeated here.

[0163] S143A: For each examination room in each examination room group, determine the set of candidates corresponding to the examination room according to the order of the first feature space distance from far to near; or, for each examination room in each examination room group, assign the candidates corresponding to the first feature space distance greater than the preset threshold to the set of candidates corresponding to the examination room.

[0164] After obtaining the spatial distance calculation result, the examinees can be allocated to each examination room of each examination room group. The corresponding features of step S143A can refer to step S142.

[0165] In other embodiments, the historical score information of the examinees can also be considered when assigning examinees, and the historical score information of the examinees can be vectorized. Thus, the examinee information can be analyzed in multiple dimensions, not only considering the group association characteristics, but also taking the examinee's ability level characteristics into consideration.

[0166] In the embodiment of the present invention, Figure 6 As shown, the examination room arrangement method may also include:

[0167] S120': Map the historical score information into a second feature vector that represents the characteristics of the examinee's ability level.

[0168] In this embodiment, the examinee's historical score information can be mapped into a second feature vector to characterize the examinee's ability level characteristics. For example, information on multiple dimensions such as single subject history scores, comprehensive scores, and score fluctuations can be integrated into one feature vector.

[0169] For other features of vectorizing the historical performance information, reference may be made to step S120 , which will not be described in detail here.

[0170] S130': Determine a plurality of second reference vectors corresponding to a preset examination room.

[0171] Accordingly, a plurality of second reference vectors corresponding to preset examination rooms may also be determined, and these reference vectors represent the distribution characteristics of the ability levels of examinees expected in different examination rooms.

[0172] In this embodiment, the second eigenvector distribution characteristics of all examinees can also be determined, and based on these distribution characteristics, a suitable second reference vector can be determined for each preset examination room, such as but not limited to statistical distribution of values ​​in various dimensions, including statistical characteristics such as mean and variance.

[0173] In a specific embodiment, the second reference vector can also be determined based on the uniform division of the feature distribution. In this specific example, assuming that there are N preset examination rooms, N second reference vectors can be set, and based on the uniform (or quasi-uniform) division of the feature distribution, the feature space is evenly divided according to the number of examination rooms N, and the center point of each divided area is used as a reference vector. For example, for a three-dimensional feature vector, if the distribution range of the second feature component is [A, B], it can be divided into N equally spaced intervals, and the center value of each interval is used as the second component of the corresponding reference vector.

[0174] In another specific embodiment, the reference vector can be determined based on a clustering method. In this specific example, assuming that there are N preset examination rooms, N second reference vectors can be set accordingly. Based on the generation method of cluster centers, the feature vectors of all examinees can be clustered (such as K-means clustering, where K is equal to the number of preset examination rooms N), and the cluster center can be used as the reference vector. This method can better adapt to the actual distribution characteristics of the feature vector.

[0175] Optionally, random perturbations may be introduced when generating the reference vectors.

[0176] In some embodiments, there may be multiple examination rooms corresponding to the same second reference vector, for example, when the examination rooms are grouped, as further described below. In these embodiments, assuming that there are N preset examination rooms, M second reference vectors may be set (M<N), and there may be multiple examination rooms corresponding to the same second reference vector.

[0177] In addition, the validity of the benchmark vector can also be verified.

[0178] Accordingly, the examination room arrangement method, more specifically step S140, may include:

[0179] S140': Allocate a plurality of candidates to be scheduled to corresponding examination rooms according to the first feature space distance and the second feature space distance.

[0180] In this embodiment, the second feature space distance is the space distance between the second feature vector and the second reference vector.

[0181] In the embodiment of the present invention, when performing multi-dimensional analysis on examinee information, a variety of different implementation schemes may be included.

[0182] In some embodiments, when the examination rooms are grouped, a preliminary allocation may be performed based on the second reference vector, and a secondary allocation may be performed based on the first reference vector.

[0183] In these embodiments, Figure 7 As shown, step S140' may include:

[0184] S141A': Divide the examination room into multiple examination room groups.

[0185] In this embodiment, the examination rooms in the same examination room group have mutually different first reference vectors and the same second reference vector.

[0186] In some embodiments, the examination rooms are grouped by "score stratification". Thus, the examination rooms in each examination room group share the same second reference vector to ensure that the examinees in the group have similar ability levels, but maintain different first reference vectors to distinguish group association characteristics.

[0187] S142A′: Determine the second feature space distance between the second reference vector of each examination room group and the second feature vectors of at least some of the examinees to be arranged.

[0188] In these embodiments, after grouping is completed, the spatial distance between the second reference vector of each examination room group as a whole and the second characteristic vector of the examinees in the preliminary selection set of the group can be calculated. This process is performed for each examination room group as a whole to ensure that the characteristic distance is calculated for different first reference vectors (indicating different group associations) within the same score level range.

[0189] For other features of step S142A', reference may be made to steps S141 and S142A.

[0190] S143A': For each examination room group, determine the preliminary selection set corresponding to the examination room group according to the order of the second feature space distance from small to large; or, for each examination room group, assign the candidates corresponding to the second feature space distance less than the preset threshold to the preliminary selection set corresponding to the examination room group.

[0191] After the second feature space distance calculation result is obtained, examinees can be allocated to each examination room of each examination room group. For other corresponding features of step S143A', reference can be made to step S143A or S142.

[0192] S144A′: Determine the first feature space distance between the first reference vector of each examination room in each examination room group and the first feature vector of the examinee in the preliminary selection set.

[0193] In some embodiments, after determining the preliminary selection set, the difference between the group association characteristics of the examinees and the examination room benchmark is further calculated. This step is used to distinguish the group association characteristics among examinees with similar ability levels. Other corresponding features of this step S144A' can refer to steps S141, S142A, and S142A'.

[0194] S145A': For each examination room in each examination room group, determine the set of candidates corresponding to the examination room in order from far to near; or, for each examination room in each examination room group, assign the candidates corresponding to the first feature space distance greater than a preset threshold to the set of candidates corresponding to the examination room.

[0195] In these embodiments, after the first spatial distance calculation result is obtained, examinees may be allocated to each examination room of each examination room group. The corresponding features of step S145A' may refer to step S143A and step S142.

[0196] Therefore, in these embodiments, the final allocation of examinees is performed within each examination room group. It can be selected to allocate in the order of the first feature space distance from far to near, or to allocate examinees whose distance is greater than a preset threshold to the corresponding examination room. This ensures that examinees in the same examination room have similar ability levels and maintain sufficient group-related feature differences.

[0197] In other embodiments, when performing a multi-dimensional analysis on the examinee information, a preliminary allocation can be performed based on the first reference vector and a secondary allocation can be performed based on the second reference vector when the examination rooms are grouped.

[0198] In these embodiments, Figure 8 As shown, step S140' may include:

[0199] S141B': Divide the examination room into multiple examination room groups.

[0200] In this embodiment, the examination rooms in the same examination room group have the same first reference vector and different second reference vectors.

[0201] In these embodiments, examination rooms with the same group-related characteristic benchmarks are grouped together, but different ability level benchmarks are set within the group. This grouping method ensures the consistency of group-related characteristics at the examination room group level. In some embodiments, examination rooms in the same group may be spatially separated, for example, each examination room in the same examination room group is not on the same floor, the same building, the same school, etc.

[0202] S142B′: Determine a first feature space distance between a first reference vector of each examination room group and first feature vectors of at least some of the examinees to be arranged.

[0203] In these embodiments, after grouping is completed, the spatial distance between the first reference vector of each examination room group as a whole and the first characteristic vector of the examinees in the preliminary selection set of the group can be calculated. This process is performed for each examination room group as a whole to ensure that the characteristic distance is calculated with the same first reference vector (indicating different group associations) but different second reference vectors (within different achievement level ranges).

[0204] For other features of step S142B', reference may be made to steps S141, S142A, and S142A'.

[0205] S143B': For each examination room group, determine the preliminary selection set corresponding to the examination room group according to the order of the first feature space distance from far to near; or, for each examination room group, assign the candidates corresponding to the first feature space distance greater than the preset threshold to the preliminary selection set corresponding to the examination room group.

[0206] After the first feature space distance calculation result is obtained, examinees can be allocated to each examination room of each examination room group. For other corresponding features of step S143B', reference can be made to steps S143A, S142, and step S143A'.

[0207] S144B′: Determine the second feature space distance between the second reference vector of each examination room in each examination room group and the second feature vector of the examinees in the preliminary selection set.

[0208] In some embodiments, after determining the preliminary selection set, the matching degree between the ability level characteristics of the examinees and the examination room benchmark is further calculated. This step is used to distinguish the ability levels among examinees with sufficient differences in group-related characteristics.

[0209] Other corresponding features of step S144B' may refer to steps S141, S142A, S142A', S144A', and S142B'.

[0210] S145B': For each examination room in each examination room group, determine the set of candidates corresponding to the examination room according to the order of the second feature space distance from small to large; or, for each examination room in each examination room group, assign the candidates corresponding to the second feature space distance less than the preset threshold to the set of candidates corresponding to the examination room.

[0211] In these embodiments, after the second spatial distance calculation result is obtained, examinees may be allocated to each examination room of each examination room group. The corresponding features of step S145B' may refer to steps S143A, S142, and S145A'.

[0212] Therefore, in these embodiments, the final allocation of examinees is performed within each examination room group. It can be selected to allocate in the order of small to large second feature space distance, or to allocate examinees whose distance is less than a preset threshold to the corresponding examination room. This ensures that examinees in the same examination room have similar ability levels while maintaining sufficient group-related feature differences.

[0213] In other embodiments, when performing multi-dimensional analysis on candidate information, a weighted combination comprehensive scoring strategy can be adopted to integrate group association characteristics and ability level characteristics into a unified metric through weight coefficients, thereby achieving one-step candidate allocation.

[0214] In these embodiments, Fig. 9 As shown, step S140' may include:

[0215] S141C′: Determine a first feature space distance between a first reference vector of each examination room and first feature vectors of at least some of the examinees to be arranged.

[0216] In the embodiment of the present invention, for each examination room, the first feature space distance between the first reference vector of the examination room and the first feature vectors of all or part of the arranged examinees can be determined respectively.

[0217] The corresponding features of step S141C' may refer to steps S141, S142A, S142A', S144A', and S142B'.

[0218] S142C′: Determine the second feature space distance between the second reference vector of each examination room and the second feature vectors of at least some of the examinees to be arranged.

[0219] In the embodiment of the present invention, for each examination room, the second feature space distance between the second reference vector of the examination room and the second feature vectors of all or part of the arranged examinees can be determined respectively.

[0220] The corresponding features of step S142C' may refer to steps S141, S142A, S142A', S144A', S142B', and S141C'.

[0221] S143C': Determine the weighted combined comprehensive feature space distance of each examination room according to the first weight coefficient of the first feature space distance and the second weight coefficient of the second feature space distance.

[0222] In these embodiments, the first weight coefficient and the second weight coefficient are opposite in sign.

[0223] In some embodiments, the system integrates the two feature distances into a comprehensive score by setting opposite weight coefficients. For example, the first weight coefficient can be set to a positive value and the second weight coefficient can be set to a negative value, so that the combination with a greater difference in group-related features and a smaller difference in ability level will receive a higher comprehensive score, and vice versa.

[0224] S144C': For each examination room, determine the set of candidates corresponding to the examination room according to the order of the size of the comprehensive feature space distance; or, for each examination room, determine the set of candidates corresponding to the examination room according to the comparison result of the comprehensive feature space distance and the preset threshold.

[0225] In these embodiments, after obtaining the calculation result of the weighted combined comprehensive feature space distance, the candidate allocation can be performed for each examination room of each examination room group. Here, the order of size described in step S144 C' can be determined according to the setting of the weight coefficient. For example, according to the comprehensive feature space distance determined by the first weight coefficient being a positive value and the second weight coefficient being a negative value, the order can be from large to small; and vice versa. Similarly, the threshold comparison described in step S144 C' can also be determined according to the setting of the weight coefficient. Other features of this step S144C' can refer to steps S143A, S142, S145A', and S145B'.

[0226] Therefore, in these embodiments, examinees can be assigned based on the comprehensive feature space distance. This approach can simultaneously meet the dual needs of preventing the risk of cheating due to interpersonal relationships and the risk of cheating due to grade dependence in a single assignment process.

[0227] Continue to refer Fig.10 In some embodiments, after the set of examinees assigned to each examination room is (preliminarily) determined, a deduplication process may be optionally introduced.

[0228] In these embodiments, Fig.10 As shown, step S140 or step S140' may further include:

[0229] S146: Check whether there are duplicate candidates in the candidate sets of each examination room.

[0230] In some embodiments, the allocation results of all examination rooms can be checked to identify candidates who are simultaneously allocated to multiple examination rooms, and then subsequent processing can be performed to ensure that each candidate is ultimately allocated to only one examination room.

[0231] S147: The duplicated candidates are temporarily stored in the waiting list.

[0232] In some embodiments, duplicated examinees may be temporarily removed from all relevant examination rooms and stored in a waiting pool.

[0233] S148: Based on the first feature space distance and the remaining capacity of each examination room, the candidates in the candidate set are reallocated to the examination room with remaining capacity.

[0234] In some embodiments, the examinees in the candidate set may be secondary allocated. Here, the remaining capacity of the examination room and the difference in group-related characteristics may be considered simultaneously to ensure that each examinee can be allocated a seat in the examination room while meeting the basic requirements for anti-cheating. Here, the examinee may be allocated to an examination room with a larger first feature space distance and remaining capacity to avoid overflow of the examination room capacity.

[0235] In the embodiment of the present invention, when the candidate combination corresponding to the examination room is determined, the seats in the examination room can be arranged in a sequential or random manner.

[0236] In some preferred embodiments, seats in the examination room may be allocated in a dynamic random manner, thereby further reducing or preventing the risk of collusion and cheating.

[0237] In these embodiments, Fig.11 As shown, the examination room arrangement method may also include:

[0238] S150: Dynamically randomize seats for candidates assigned to each examination room.

[0239] like Fig.12 It is further shown that step S150 may include:

[0240] S151: Generate a random number seed based on the examination room number.

[0241] In some embodiments, a unique random number seed may be generated for each examination room. In further embodiments, the random number seed may also be generated based on the examination room number and the system timestamp to further achieve dynamic randomized seat allocation.

[0242] S152: Based on the random number seed, hash operation is performed on the candidate numbers of each examination room to obtain a random seat vector.

[0243] In some embodiments, the candidate number includes the admission ticket number, identity card number, or the above-mentioned identification information or part thereof (such as the student number).

[0244] In some embodiments, the time dimension can be used to enhance randomness. In some embodiments, a hash algorithm can be used to combine the examinee number and the random number seed to generate a random seat vector. In these embodiments, a random number seed with time validity can be generated by performing a specific combination operation (such as concatenation, XOR, etc.) on the examination room number and the system timestamp at the time of generation to ensure that each generated random sequence is unique.

[0245] S153: Randomly sort the seats of the examinees in each examination room based on the seat random vector.

[0246] In this embodiment, the dynamic randomized seat allocation mechanism can further reduce or resolve the risk of cheating due to advance collusion that may result in cheating due to the possibility that the examination room arrangement information or rules may be known in advance.

[0247] In a preferred embodiment, the random number seed and the randomly sorted seat distribution information can be encrypted and stored separately. For example, in the case of a computer-based test, such separate storage can be more conducive to reducing the risk of collusion and cheating.

[0248] In some embodiments of the present invention, Fig.13 As shown, a test room arrangement device 1300 is also provided, which may at least include: an acquisition unit 1310, a mapping unit 1320, a reference unit 1330 and an allocation unit 1340. The acquisition unit 1310 may be configured to acquire candidate information of a plurality of candidates to be arranged, wherein the candidate information includes identification information. The (first) mapping unit 1320 may be configured to map the identification information into a first feature vector representing the correlation characteristics of the candidate group. The (first) reference unit 1330 may be configured to determine a plurality of first reference vectors corresponding to a preset test room. The allocation unit 1340 may be configured to allocate the plurality of candidates to be arranged to corresponding test rooms at least according to a first feature space distance, wherein the first feature space distance is a space distance between a first feature vector and a first reference vector.

[0249] Optionally, the examination room arrangement device may further include a second mapping unit and a second reference unit. The second mapping unit may be configured to map the historical score information into a second feature vector that characterizes the ability level characteristics of the examinee. The second reference unit may be configured to determine a plurality of second reference vectors corresponding to the preset examination room. Accordingly, the allocation unit may be configured to allocate the plurality of examinees to be arranged to the corresponding examination room according to the first feature space distance and the second feature space distance, wherein the second feature space distance is the space distance between the second feature vector and the second reference vector.

[0250] In embodiments of the present invention, method features may be combined with apparatus to obtain new embodiments, and vice versa.

[0251] In some embodiments of the present invention, Fig.14 As shown, an electronic device is provided, which includes a processor and a memory storing a computer program, and the processor is configured to implement any method of the embodiments of the present invention when running the computer program.

[0252] Fig.14 A schematic diagram of an electronic device 1400 that can be used to implement a method or implement an embodiment of the present invention is shown. In some embodiments, the number of electronic devices may be more or less than the number shown. In some embodiments, a single or multiple electronic devices may be used for implementation. In some embodiments, cloud or distributed electronic devices may also be used for implementation.

[0253] like Fig.14As shown, the electronic device 1400 includes a processor 1401 and a memory 1402. The processor is used to execute programs stored in the memory, and these programs can implement the methods, steps or functions described in the above embodiments when the computer executes them. The processor 1401 may include various types of processors, such as a central processing unit (CPU), a graphics processing unit (GPU), a neural network processor (NPU), a digital signal processor (DSP), etc. The processor 1401 and the memory 1102 are interconnected through a bus 1403. The bus 1403 can also be connected to an input / output (I / O) interface, etc. The system, device, module or unit illustrated in the above embodiments can be implemented by a computer or its associated components. The computer can be, for example, a mobile terminal, a smart phone, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a personal digital assistant, a media player, a navigation device, a game console, a tablet computer, a wearable device, a smart TV, an Internet of Things system, a smart home, an industrial computer, a server or a combination thereof.

[0254] Although not shown, in an embodiment of the present invention, a program product is provided, including a computer program, and when the computer program is executed by a processor, the method of any one of the embodiments of the present invention is implemented.

[0255] Although not shown, in an embodiment of the present invention, a storage medium is provided, the storage medium storing a computer program, the computer program being configured to implement any method of the embodiments of the present invention when executed.

[0256] Storage media in embodiments of the present invention include permanent and non-permanent, removable and non-removable items that can be used to store information by any method or technology. Examples of storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0257] The methods, programs, systems, devices, etc. of the embodiments of the present invention may be executed or implemented in a single or multiple networked computers, or may be practiced in a distributed computing environment. In the embodiments of this specification, in these distributed computing environments, tasks may be performed by remote processing devices connected via a communication network.

[0258] Those skilled in the art should understand that the embodiments of the present specification may be provided as methods, systems or computer program products. Therefore, those skilled in the art may imagine that the functional modules / units or controllers and related method steps described in the above embodiments may be implemented in software, hardware or a combination of software / hardware.

[0259] Unless explicitly stated, the actions or steps of the methods, programs, and embodiments of the present invention do not have to be performed in a specific order and can still achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0260] In this article, multiple embodiments of the present invention are described, but for the sake of brevity, the description of each embodiment is not exhaustive, and the same or similar features or parts between the embodiments may be omitted. In this article, "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" are meant to be applicable to at least one embodiment or example according to the present invention, but not all embodiments. The above terms do not necessarily mean to refer to the same embodiment or example. In the absence of contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples.

[0261] The exemplary systems and methods of the present invention have been specifically shown and described with reference to the above embodiments, which are merely examples of the best modes for implementing the present systems and methods. It will be appreciated by those skilled in the art that various changes may be made to the embodiments of the systems and methods described herein when implementing the present systems and / or methods without departing from the spirit and scope of the present invention as defined in the appended claims.

Claims

1. A method for arranging an examination room, characterized in that: include: Acquire candidate information of a plurality of candidates to be scheduled, wherein the candidate information includes identification information; Mapping the identification information into a first feature vector representing the correlation characteristics of the examinee group; Determine a plurality of first reference vectors corresponding to a preset examination room; as well as The plurality of candidates to be scheduled are allocated to corresponding examination rooms at least according to a first feature space distance, wherein the first feature space distance is a space distance between the first feature vector and the first reference vector.

2. The method for arranging examination rooms according to claim 1, characterized in that: The step of allocating the plurality of candidates to be scheduled to corresponding examination rooms at least according to the first feature space distance includes: Determine a first feature space distance between a first reference vector of each examination room and first feature vectors of at least some of the examinees to be arranged; and For each examination room, the set of candidates corresponding to the examination room is determined according to the order of the first feature space distance from far to near; or, for each examination room, the candidates corresponding to the first feature space distance greater than a preset threshold are assigned to the set of candidates corresponding to the examination room.

3. The method for arranging examination rooms according to claim 1, characterized in that: The candidate information also includes historical score information; The step of allocating the plurality of candidates to be scheduled to corresponding examination rooms at least according to the first feature space distance includes: According to the score range determined by the historical score information, the examination room is divided into a plurality of examination room groups, and a preliminary selection set corresponding to each examination room group is determined, wherein the historical scores of the examinees in the preliminary selection set of each examination room group are within the score range corresponding to the examination room group; Determine a first feature space distance between a first reference vector of each examination room in each examination room group and a first feature vector of an examinee in the preliminary selection set; and For each examination room in each examination room group, the set of candidates corresponding to the examination room is determined according to the order of the first feature space distance from far to near; or, for each examination room in each examination room group, the candidates corresponding to the first feature space distance greater than the preset threshold are assigned to the set of candidates corresponding to the examination room.

4. The method for arranging examination rooms according to claim 1, characterized in that: The candidate information also includes historical score information; The method further comprises: Mapping the historical score information into a second feature vector representing the ability level of the examinee; and Determining a plurality of second reference vectors corresponding to the preset examination room; The allocating the multiple candidates to be scheduled to corresponding examination rooms at least according to the first feature space distance includes: allocating the multiple candidates to be scheduled to corresponding examination rooms according to the first feature space distance and the second feature space distance, wherein the second feature space distance is the space distance between the second feature vector and the second reference vector.

5. The method for arranging examination rooms according to claim 4, characterized in that: The allocating the plurality of candidates to be arranged to corresponding examination rooms according to the first feature space distance and the second feature space distance comprises: Dividing the examination room into a plurality of examination room groups, wherein examination rooms in the same examination room group have different first reference vectors and the same second reference vector; Determine a second feature space distance between a second reference vector of each examination room group and second feature vectors of at least some of the examinees to be arranged; For each examination room group, determine the preliminary selection set corresponding to the examination room group according to the order of the second feature space distance from small to large; or, for each examination room group, assign the examinees corresponding to the second feature space distance less than a preset threshold to the preliminary selection set corresponding to the examination room group; Determine a first feature space distance between a first reference vector of each examination room in each examination room group and a first feature vector of an examinee in the preliminary selection set; For each examination room in each examination room group, the set of candidates corresponding to the examination room is determined in order from far to near; or, for each examination room in each examination room group, the candidates corresponding to the first feature space distance greater than a preset threshold are assigned to the set of candidates corresponding to the examination room.

6. The method for arranging examination rooms according to claim 4, characterized in that: The allocating the plurality of candidates to be arranged to corresponding examination rooms according to the first feature space distance and the second feature space distance comprises: Dividing the examination room into a plurality of examination room groups, wherein examination rooms in the same examination room group have the same first reference vector and different second reference vectors; Determine a first feature space distance between a first reference vector of each examination room group and first feature vectors of at least some of the examinees to be arranged; For each examination room group, determine the preliminary selection set corresponding to the examination room group according to the order of the first feature space distance from far to near; or, for each examination room group, assign the examinees corresponding to the first feature space distance greater than a preset threshold to the preliminary selection set corresponding to the examination room group; Determining a second feature space distance between a second reference vector of each examination room in each examination room group and a second feature vector of an examinee in the preliminary selection set; and For each examination room in each examination room group, the set of candidates corresponding to the examination room is determined according to the order of the second feature space distance from small to large; or, for each examination room in each examination room group, the candidates corresponding to the second feature space distance less than the preset threshold are assigned to the set of candidates corresponding to the examination room.

7. The method for arranging examination rooms according to claim 4, characterized in that: The allocating the plurality of candidates to be arranged to corresponding examination rooms according to the first feature space distance and the second feature space distance comprises: Determine a first feature space distance between a first reference vector of each examination room and first feature vectors of at least some of the examinees to be arranged; Determine a second feature space distance between a second reference vector of each examination room and a second feature vector of at least part of the examinees to be arranged; Determining a weighted combined comprehensive feature space distance of each examination room according to a first weight coefficient of the first feature space distance and a second weight coefficient of the second feature space distance, wherein the first weight coefficient and the second weight coefficient are opposite in sign; and For each examination room, the set of candidates corresponding to the examination room is determined according to the order of the size of the comprehensive feature space distance; or, for each examination room, the set of candidates corresponding to the examination room is determined according to the comparison result of the comprehensive feature space distance with a preset threshold.

8. The method for arranging examination rooms according to any one of claims 2 to 7, characterized in that: The step of allocating the plurality of candidates to be arranged to corresponding examination rooms at least according to the first feature space distance further includes: Detecting whether there are duplicated candidates in the set of candidates in each examination room; Temporarily storing the duplicated candidates in the waiting list; According to the first feature space distance and the remaining capacity of each examination room, the examinees in the candidate set are reallocated to the examination room with remaining capacity.

9. The method for arranging examination rooms according to any one of claims 1 to 7, characterized in that: The method further comprises: Dynamically randomize seats for candidates assigned to each examination room, including: Generate a random number seed based on the exam room number; According to the random number seed, a hash operation is performed on the candidate number of each examination room to obtain a seat random vector; and The seats of the examinees in each examination room are randomly sorted based on the seat random vector.

10. The method for arranging examination rooms according to any one of claims 1 to 7, characterized in that: The identification information includes student ID information, and mapping the identification information into a first feature vector representing a correlation feature of a group of examinees includes: Based on the preset information extraction rules, the year information, class information, and serial number information are parsed from the student ID information; Mapping the year information into a first characteristic component representing a time correlation; Mapping the class information into a second feature component representing a degree of group association; Mapping the serial number information into a third characteristic component representing individual distinction; and The first feature component, the second feature component and the third feature component are combined and processed to generate the first feature vector.

11. The method for arranging examination rooms according to claim 1, characterized in that: The identification information includes school number and student number information, and the mapping of the identification information into a first feature vector representing the correlation characteristics of the examinee group includes: Based on a preset information extraction rule, the school information is obtained from the school number, and the year information, class information, and serial number information are obtained from the student number information; Mapping the year information into a first characteristic component representing a time correlation; Mapping the class information into a second feature component representing a degree of group association; Mapping the serial number information into a third characteristic component representing individual distinction; Mapping the school information into a fourth characteristic component representing the degree of institutional relevance; and The first feature component, the second feature component, the third feature component and the fourth feature component are combined and processed to generate the first feature vector.

12. A device for arranging examination rooms, characterized in that: include: An acquisition unit, configured to acquire candidate information of a plurality of candidates to be scheduled, wherein the candidate information includes identification information; A mapping unit, configured to map the identification information into a first feature vector representing a correlation feature of a group of examinees; A reference unit, configured to determine a plurality of first reference vectors corresponding to a preset examination room; as well as The allocating unit is configured to allocate the plurality of candidates to be scheduled to corresponding examination rooms at least according to a first feature space distance, wherein the first feature space distance is a space distance between the first feature vector and the first reference vector.

13. An electronic device, characterized in that: include: A processor and a memory storing a computer program, wherein the processor is configured to implement the method according to any one of claims 1 to 11 when executing the computer program.

14. A program product, characterized in that The method comprises a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images