Student comprehensive evaluation method and device, storage medium and electronic equipment

Abstract

The invention discloses a student comprehensive evaluation method and device, a storage medium and electronic equipment. The method comprises the following steps: converting student information data in a student information database through a student information reader to obtain a data text fragment; synthesizing the data text fragments into an electronic document based on a student information synthesizer; converting the electronic document into a large model cue word through an evaluation cue word generator and an evaluation template library; and calling the large language model, and converting the large model cue word into a student evaluation report according to the large language model. Through the method and the device, the problem that comprehensive evaluation on students is not comprehensive based on student information data in the related technology is solved.

Description

Background Art

[0002] Among the related technologies, student evaluation is extremely important in the field of education. It can not only comprehensively and objectively reflect students' learning situation and development level, and provide students with a direction for self-cognition and development, but also provide a basis for teachers to improve teaching methods and teaching quality. At the same time, student evaluation helps promote educational reform and promote educational equity. In addition, it can also guide students to establish correct values ​​and goals, stimulate students' learning motivation and potential, and have a far-reaching impact on students' growth and future development.

[0003] Student evaluation has many dimensions and is frequent. Teachers need to master rich professional knowledge to accurately evaluate. Understanding students' data is the basis of evaluation, and mastering the evaluation format template can make the evaluation more standardized and scientific. At present, many schools still use manual subjective evaluation, and the content of the evaluation is relatively concise.

[0004] There is currently no effective solution to the problem that the comprehensive evaluation of students based on student information data in relevant technologies is not comprehensive enough. Summary of the invention

[0005] The main purpose of this application is to provide a student comprehensive evaluation method, device, storage medium and electronic device to solve the problem in related technologies that the comprehensive evaluation of students based on student information data is not comprehensive enough.

[0006] In order to achieve the above-mentioned purpose, according to the first aspect of the present application, a method for comprehensive evaluation of students is provided. The method comprises: converting the student information data in the student information database by a student information interpreter to obtain data text segments; synthesizing the data text segments into electronic documents based on a student information synthesizer; converting the electronic documents into large model prompt words by an evaluation prompt word generator and an evaluation template library; calling a large language model, and converting the large model prompt words into a student evaluation report based on the large language model.

[0007] Furthermore, the student information interpreter includes: an interpretation rule database and an interpretation template database. The student information data in the student information database is converted by the student information interpreter to obtain data text fragments, including: interpreting the student information data based on the interpretation rule database to obtain interpreted student data, wherein the interpretation rule database includes at least one of the following: threshold division rules, range division rules, percentile division rules, and change ratio division rules; inputting the interpreted student data into the interpretation template database to convert the student information data to obtain data text fragments, wherein the interpretation template database includes at least one of the following: detailed information template, status description template, year-on-year description template, quarter-on-quarter description template, competition results template, competition experience template, reward and commendation template, and punishment warning template.

[0008] Furthermore, the types of student information synthesizers include at least one of the following: test score synthesizer, classroom performance synthesizer, and comprehensive performance synthesizer. Synthesizing data text segments into electronic documents based on the student information synthesizer includes: reading target data in a student information database based on the student information synthesizer; calling student information interpreters in sequence based on the target data to generate data text segments corresponding to the target data; when it is recognized that the student information interpreter has completed the task of generating data text segments, synthesizing the data text segments corresponding to the target data in a preset order to obtain an electronic document.

[0009] Furthermore, after calling the student information interpreter in sequence based on the target data to generate data text segments corresponding to the target data, the method also includes: judging whether the student information interpreter has completed the task of generating the data text segments; if it is identified that the student information interpreter has completed the generation task, executing the step of synthesizing the data text segments corresponding to the target data in a preset order to obtain an electronic document; if it is identified that the student information interpreter has not completed the generation task, repeating the step of calling the student information interpreter in sequence based on the target data to generate the data text segments corresponding to the target data.

[0010] Furthermore, the electronic document is converted into large model prompt words through an evaluation prompt word generator and an evaluation template library, including: identifying user evaluation dimensions in the electronic document based on the evaluation prompt words; setting an evaluation template library corresponding to the user evaluation dimensions, and converting the electronic document into large model prompt words based on the evaluation template library, wherein the large model prompt words include at least one of the following: role, goal, skill, input, and output.

[0011] Furthermore, the evaluation template library is used to define the word count range and precautions of the electronic document, and the evaluation template library includes at least one of the following: academic performance evaluation, moral behavior evaluation, innovation ability evaluation, and comprehensive ability evaluation.

[0012] Further, the large language model is called, and the large model prompt words are converted into a student evaluation report based on the large language model, including: calling the large language model through an application program interface; reasoning the large model prompt words based on the large language model to obtain a student evaluation report.

[0013] In order to achieve the above-mentioned purpose, according to the second aspect of the present application, a student comprehensive evaluation device is provided. The device comprises: a first conversion unit, which is used to convert the student information data in the student information database through a student information interpreter to obtain a data text segment; a synthesis unit, which is used to synthesize the data text segment into an electronic document based on the student information synthesizer; a second conversion unit, which is used to convert the electronic document into a large model prompt word through an evaluation prompt word generator and an evaluation template library; and a calling unit, which is used to call a large language model and convert the large model prompt word into a student evaluation report based on the large language model.

[0014] According to a third aspect of an embodiment of the present application, there is provided an electronic device, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned comprehensive student evaluation methods is implemented.

[0015] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a comprehensive student evaluation method according to any one of the above items is implemented.

[0016] Through this application, the following steps are adopted: converting the student information data in the student information database through a student information interpreter to obtain data text fragments; synthesizing the data text fragments into electronic documents based on a student information synthesizer; converting the electronic documents into large model prompt words through an evaluation prompt word generator and an evaluation template library; calling a large language model, and converting the large model prompt words into a student evaluation report based on the large language model. Through this application, the problem of insufficient comprehensive evaluation of students based on student information data in related technologies is solved. By converting the large model prompt words into a student evaluation report based on a large language model. Thus, the effect of comprehensive and integrated evaluation of students is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 is a flow chart of a comprehensive student evaluation method provided according to an embodiment of the present application;

[0019] Figure 2 is a schematic diagram of a student information interpreter architecture provided according to an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of a student information interpreter architecture provided according to an embodiment of the present application;

[0021] Figure 4is a schematic diagram of the overall architecture of comprehensive student evaluation according to an embodiment of the present application;

[0022] Figure 5 is a schematic diagram of a student comprehensive evaluation device provided according to an embodiment of the present application;

[0023] Figure 6 It is a schematic diagram of the network architecture of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to an embodiment of the present application, a method for comprehensive evaluation of students is provided.

[0028] Figure 1 is a flow chart of a comprehensive student evaluation method according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0029] Step S101, converting the student information data in the student information database through a student information interpreter to obtain data text segments.

[0030] Among them, the student information database is used to record students' basic information data, for example, based on a relational database to store students' basic information, test scores, absence records, classroom performance, reward and punishment records, lateness and early departure records, competition participation records, etc.

[0031] For example, the database table structure design for establishing basic student information is as follows:

[0032]

[0033] The above design is mainly to meet the needs of effective management and statistics of student information. By recording basic information such as student ID and name, it is easy to accurately identify and locate individual students; recording school club positions, class cadre positions, etc., can understand students' participation in campus activities; and recording hobbies and specialties helps to discover students' potential and personality characteristics, which is a good way to provide personalized education.

[0034] Provide reference for education and training.

[0035] For another example, create a student exam score table: record the student's exam scores for each exam, including final exams, midterm exams, monthly exams, etc. The specific database table structure design is as follows:

[0036]

[0037] Establish a student absence record table: record the time, category, and duration of each student's absence. The specific database table structure is designed as follows:

[0038]

[0039]

[0040] Establish a student lateness and early departure record table: record each student's lateness or early departure, including time and duration, etc. The specific database table structure is designed as follows:

[0041]

[0042] Create a student classroom performance table: record the time, category, and duration of each student's absence. The specific database table structure is designed as follows:

[0043]

[0044] Establish a student reward and punishment record table: record the rewards and punishments students receive during their time at school. The specific database table structure is designed as follows:

[0045]

[0046]

[0047] Establish a student competition record table: record the students' participation in various competitions during their school years. The specific database table structure is designed as follows:

[0048]

[0049] This application records the objective data of students' daily learning through a relational database to ensure the comprehensiveness and authenticity of the evaluation and provide a solid data foundation for the evaluation.

[0050] In some embodiments, the student information interpreter includes: an interpretation rule database, an interpretation template database, and the student information data in the student information database is converted by the student information interpreter to obtain data text fragments, which can be achieved through the following steps: interpreting the student information data based on the interpretation rule database to obtain interpreted student data, wherein the interpretation rule database includes at least one of the following: threshold division rules, range division rules, percentile division rules, and change ratio division rules; inputting the interpreted student data into the interpretation template database to convert the student information data to obtain data text fragments, wherein the interpretation template database includes at least one of the following: detailed information template, status description template, year-on-year description template, quarter-on-quarter description template, competition results template, competition experience template, reward and commendation template, and punishment warning template.

[0051] The data text segments are student information segments converted into descriptive text content by the student information interpreter reading data from various tables of student information in the database. Figure 2 As shown, the student information interpreter in this case consists of an interpretation rule library and an interpretation template library. The interpretation rule library is a collection of a series of rules, including various specific rules for interpreting student information, such as threshold division, range division, percentile division, change ratio division, etc.

[0052] Specifically, the threshold division rule: directly comparing the data with the threshold is usually used to interpret whether certain behaviors or certain states exist. For example, according to the attendance records, two states can be divided: absence (absence times greater than 0) and full attendance (absence times equal to 0), as shown below:

[0053]

[0054] Range division rule: divide the data into ranges according to the value range of the data. For example, test scores can be divided into excellent (above 90 points), good (80-90 points), medium (70-80 points), pass (60-70 points) and fail (below 60 points), as shown below:

[0055]

[0056] Percentile division rule: By comparing the value with all the data, the percentile position of the value is calculated, and the division rule is based on the percentile. For example, the level of test scores can be divided into upper (top 30%), middle (between 70% and 30%), and lower (bottom 30%), as shown below:

[0057]

[0058] Change ratio classification rules: Calculate the change ratio between two values ​​of the same dimension, so that a relative change percentage can be obtained to reflect the change of the value. For example, the year-on-year change of test scores can be divided into basically unchanged (change ratio within 5%), slightly fluctuated (change ratio between 5% and 10%), and greatly fluctuated (change ratio above 10%), as shown below:

[0059]

[0060] Among them, the interpretation template library in this case is a set of pre-designed text templates, which are used to calculate student information based on the rule library (interpreted student data) and then describe it according to specific formats and sentences. The template library provides a standardized way of expressing student information in the interpretation database, that is, the data text fragments in this case. The templates include detailed information, status description, year-on-year description, month-on-month description, competition results, competition experience, rewards and punishments, punishment warnings, classroom performance, etc. The following is a description of some of the templates. The content in brackets [] should be calculated based on data values ​​or rule libraries.

[0061] Detailed information template:

[0062]

[0063] Status description template:

[0064]

[0065] Year-on-year description template:

[0066]

[0067] MoM description template:

[0068]

[0069] Competition results template:

[0070]

[0071] Competition experience template:

[0072]

[0073] Rewards and recognition template:

[0074]

[0075] Penalty warning template:

[0076]

[0077] This application uses a rich library of interpretation rules and interpretation templates to convert various quantitative data into vivid and specific descriptive text fragments, making the evaluation more readable and understandable.

[0078] Step S102, synthesizing the data text segments into an electronic document based on the student information synthesizer.

[0079] The information decoder obtains text fragments describing various aspects of student information. The function of the student information synthesizer is to combine these text fragments into a clear structured document, thereby ensuring that the synthesized electronic archive is accurate, clear and organized. First, according to the information synthesis requirements, relevant data is read from the student information database, and then the decoder converts these data into text fragments, and then classifies these text fragments according to certain orders and rules and combines them into a complete electronic archive.

[0080] In some embodiments, the type of student information synthesizer includes at least one of the following: test score synthesizer, classroom performance synthesizer, and comprehensive performance synthesizer. The data text segments are synthesized into an electronic document based on the student information synthesizer, which can be obtained by the following steps: reading the target data in the student information database based on the student information synthesizer; calling the student information interpreter in sequence based on the target data to generate the data text segments corresponding to the target data; when it is recognized that the student information interpreter has completed the task of generating the data text segments, the data text segments corresponding to the target data are synthesized in a preset order to obtain an electronic document.

[0081] Specifically, in order to meet various evaluation requirements, including comprehensive evaluation of students, single subject evaluation, classroom evaluation, unilateral ability evaluation, etc., this solution needs to have built-in various information synthesizers for users to choose from, including a synthesizer of student Si's test scores in year Yj, a synthesizer of student Si's classroom performance in subject Kj, a synthesizer of student Si's comprehensive ability in category Tj, a synthesizer of student Si's comprehensive performance in subject Kj, etc.

[0082] Specifically, after calling the student information interpreter in sequence based on the target data to generate data text segments corresponding to the target data, the method also includes: judging whether the student information interpreter has completed the task of generating the data text segments; if it is identified that the student information interpreter has completed the generation task, executing the step of synthesizing the data text segments corresponding to the target data in a preset order to obtain an electronic document; if it is identified that the student information interpreter has not completed the generation task, repeating the step of calling the student information interpreter in sequence based on the target data to generate the data text segments corresponding to the target data.

[0083] For example, Figure 3 As shown, taking the test score synthesizer of student Si in Yj as an example, the information synthesizer first accesses the student information database to read the basic information of student Si and the test scores of each subject of student Si from Yj-1 to Yj. First, the basic information is converted into a text segment S1 through the student detailed information interpreter, and then the status description, year-on-year description, and quarter-on-quarter description templates are called for each subject in turn to generate the results, levels, year-on-year and quarter-on-quarter situations of the student's scores to generate text segments Si, and it is determined whether the generation task has been processed. If it is completed, these text segments S1, S2, S3...Sn are finally combined according to the format of the template. Among them, the preset order in this case can be time order, category order, etc. The preset order is not fixed and can be adjusted according to the actual situation or changes in demand. If it is not completed, the relevant information is converted into text segments Si through the corresponding interpreter.

[0084] The information synthesizer of this application skillfully integrates different descriptive text fragments according to certain rules to form a complete electronic archive, showing the comprehensive performance of students, and embodies a high degree of integration and intelligence.

[0085] Step S103: converting the electronic document into large model prompt words through the evaluation prompt word generator and the evaluation template library.

[0086] Among them, evaluation prompt words are usually a series of keywords, phrases or sentences generated by the evaluation prompt word generator, and large model prompt words refer to prompt words used in large models (such as large language models). These prompt words are designed to guide the large model to generate output of a specific type or format.

[0087] Specifically, the electronic document is converted into large model prompt words through the evaluation prompt word generator and the evaluation template library, which can be obtained through the following steps: identifying the user evaluation dimensions in the electronic document based on the evaluation prompt words; setting the evaluation template library corresponding to the user evaluation dimensions, and converting the electronic document into large model prompt words based on the evaluation template library, wherein the large model prompt words include at least one of the following: role, goal, skill, input, and output.

[0088] For example, the student evaluation prompt word generator sets the role (#Role), goal (#Goals), skills (#Skills), input (#InputContent), output (#OutputFormat) and attention (#Attention) of the big model in this evaluation task according to the evaluation dimensions selected by the user, and guides the big model to complete the generation of evaluation content. The input information comes from the content generated by calling the student information synthesizer, and the output requirements are set according to the built-in evaluation template. Take the prompt words for the comprehensive evaluation of student Si's test scores in year Yj as an example,

[0089]

[0090] This application helps guide the evaluation process, stimulate more valuable information and opinions, and enhance the depth and breadth of the evaluation through the structured design of the prompt word template library.

[0091] Among them, the evaluation template library is used to define the word count range and precautions of the electronic document. The evaluation template library includes at least one of the following: academic performance evaluation, moral behavior evaluation, innovation ability evaluation, and comprehensive ability evaluation.

[0092] In other words, the evaluation template library is positioned to provide users with a series of standardized evaluation templates, so that users can conduct comprehensive, objective and accurate evaluations of students in different scenarios. The template defines the evaluation dimensions, word count range, and precautions of the report. The template library has built-in templates of various types, such as academic performance evaluation, moral behavior evaluation, innovation ability evaluation, and comprehensive ability evaluation.

[0093] Step S104, calling the large language model, and converting the large model prompt words into a student evaluation report according to the large language model.

[0094] Specifically, calling the large language model and converting the large model prompt words into a student evaluation report based on the large language model can be achieved through the following steps: calling the large language model through an application programming interface; reasoning about the large model prompt words based on the large language model to obtain a student evaluation report.

[0095] Specifically, this solution adopts the Ollma mode to deploy and run the Qianwen big model, calls the big language model for reasoning according to the Ollma service program interface, and outputs the corresponding student evaluation report. This application makes use of the big model reasoning capability, that is, through text content understanding and reasoning summary, to conduct in-depth analysis and understanding of the data, thereby generating more accurate and insightful evaluation results, realizing the automation and intelligence of student evaluation, and demonstrating the advancement and innovation of the technology.

[0096] Optionally, Figure 4is a schematic diagram of the overall architecture of the comprehensive evaluation of students according to an embodiment of the present application, such as Figure 4 As shown in the figure, the system architecture consists of a student information database, a student information interpreter, a student information synthesizer, an evaluation prompt generator, and a large language model. The student information database is used to store various records of students in daily life. The student information interpreter converts the records in the database into text fragments. The student information synthesizer is responsible for composing an electronic file with multiple text fragments converted by the interpreter according to a rule. The evaluation prompt generator generates a large model prompt according to the evaluation template and the input electronic file, and calls the large model reasoning ability to generate an evaluation report.

[0097] In summary, the student comprehensive evaluation method provided in the embodiment of the present application converts the student information data in the student information database through a student information interpreter to obtain data text fragments; synthesizes the data text fragments into electronic documents based on a student information synthesizer; converts the electronic documents into large model prompt words through an evaluation prompt word generator and an evaluation template library; calls a large language model, and converts the large model prompt words into a student evaluation report based on the large language model. Through this application, the problem that the comprehensive evaluation of students based on student information data in the related art is not comprehensive enough is solved. By converting the large model prompt words into a student evaluation report based on the large language model. Thus, the effect of comprehensive and integrated evaluation of students is achieved.

[0098] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0099] The embodiment of the present application also provides a student comprehensive evaluation device. It should be noted that the student comprehensive evaluation device of the embodiment of the present application can be used to execute the student comprehensive evaluation method provided in the embodiment of the present application. The student comprehensive evaluation device provided in the embodiment of the present application is introduced below.

[0100] Figure 5 is a schematic diagram of a student comprehensive evaluation device 500 according to an embodiment of the present application. Figure 5 As shown, the device includes: a first conversion unit 501, a synthesis unit 502, a second conversion unit 503, and a calling unit 504.

[0101] Specifically, the first conversion unit 501 is used to convert the student information data in the student information database through the student information interpreter to obtain a data text segment;

[0102] A synthesis unit 502, for synthesizing the data text segments into an electronic document based on the student information synthesizer;

[0103] The second conversion unit 503 is used to convert the electronic document into a large model prompt word through the evaluation prompt word generator and the evaluation template library;

[0104] The calling unit 504 is used to call the large language model and convert the large model prompt words into a student evaluation report according to the large language model.

[0105] In summary, the student comprehensive evaluation device provided by the embodiment of the present application converts the student information data in the student information database through the first conversion unit 501 through the student information interpreter to obtain a data text segment; the synthesis unit 502 synthesizes the data text segment into an electronic document based on the student information synthesizer; the second conversion unit 503 converts the electronic document into a large model prompt word through the evaluation prompt word generator and the evaluation template library; the calling unit 504 calls the large language model, and converts the large model prompt word into a student evaluation report based on the large language model, which solves the problem that the comprehensive evaluation of students based on student information data in the related art is not comprehensive enough. By converting the large model prompt word into a student evaluation report based on the large language model. And then achieve the effect of comprehensive and integrated evaluation of students.

[0106] Optionally, in the student comprehensive evaluation device provided in the embodiment of the present application, the student information interpreter includes: an interpretation rule database, an interpretation template database, and a first conversion unit, including: an interpretation module, used to interpret the student information data based on the interpretation rule database to obtain interpreted student data, wherein the interpretation rule database includes at least one of the following: threshold division rules, range division rules, percentile division rules, and change ratio division rules; an input module, used to input the interpreted student data into the interpretation template database to convert the student information data to obtain data text fragments, wherein the interpretation template database includes at least one of the following: detailed information template, status description template, year-on-year description template, quarter-on-quarter description template, competition results template, competition experience template, reward and commendation template, and punishment warning template.

[0107] Optionally, in the student comprehensive evaluation device provided in the embodiment of the present application, the type of the student information synthesizer includes at least one of the following: a test score synthesizer, a classroom performance synthesizer, and a comprehensive performance synthesizer. The synthesis unit includes: a reading module, which is used to read the target data in the student information database based on the student information synthesizer; a first calling module, which is used to call the student information interpreter in sequence based on the target data to generate a data text segment corresponding to the target data; and a synthesis module, which is used to synthesize the data text segment corresponding to the target data in a preset order to obtain an electronic document when it is recognized that the student information interpreter has completed the task of generating the data text segment.

[0108] Optionally, in the student comprehensive evaluation device provided in the embodiment of the present application, the device also includes: a judgment unit, which is used to judge whether the student information interpreter has completed the task of generating the data text segment after calling the student information interpreter in sequence based on the target data to generate the data text segment corresponding to the target data; a first recognition unit, which is used to execute the step of synthesizing the data text segment corresponding to the target data in a preset order to obtain an electronic document if it is recognized that the student information interpreter has completed the generation task; and a second recognition unit, which is used to repeat the step of calling the student information interpreter in sequence based on the target data to generate the data text segment corresponding to the target data if it is recognized that the student information interpreter has not completed the generation task.

[0109] Optionally, in the student comprehensive evaluation device provided in the embodiment of the present application, the second conversion unit includes: an identification module for identifying user evaluation dimensions in electronic documents based on evaluation prompt words; a setting module for setting an evaluation template library corresponding to the user evaluation dimensions, and converting the electronic document into a large model prompt word based on the evaluation template library, wherein the large model prompt word includes at least one of the following: role, goal, skill, input, and output.

[0110] Optionally, in the student comprehensive evaluation device provided in the embodiment of the present application, the evaluation template library is used to define the word count range and precautions of the electronic document, and the evaluation template library includes at least one of the following: academic performance evaluation, moral behavior evaluation, innovation ability evaluation, and comprehensive ability evaluation.

[0111] Optionally, in the student comprehensive evaluation device provided in the embodiment of the present application, the calling unit includes: a second calling module, used to call the large language model through an application program interface; and a calculation module, used to infer the large model prompt words based on the large language model to obtain a student evaluation report.

[0112] The student comprehensive evaluation device includes a processor and a memory. The first conversion unit 501, synthesis unit 502, second conversion unit 503, calling unit 504, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

[0113] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the comprehensive evaluation of students can be performed by adjusting the kernel parameters.

[0114] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0115] In the exemplary embodiment of the present application, a computer storage medium capable of implementing the above method is also provided. A program product capable of implementing the above method of the present specification is stored thereon. In some possible embodiments, various aspects of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification, such as the following steps can be performed: converting the student information data in the student information database through a student information interpreter to obtain data text fragments; synthesizing the data text fragments into electronic documents based on a student information synthesizer; converting the electronic documents into large model prompt words through an evaluation prompt word generator and an evaluation template library; calling a large language model, and converting the large model prompt words into a student evaluation report based on the large language model.

[0116] In an optional embodiment, the student information interpreter includes: an interpretation rule database, an interpretation template database, and the student information data in the student information database is converted by the student information interpreter to obtain data text fragments, including: interpreting the student information data based on the interpretation rule database to obtain interpreted student data, wherein the interpretation rule database includes at least one of the following: threshold division rules, range division rules, percentile division rules, and change ratio division rules; inputting the interpreted student data into the interpretation template database to convert the student information data to obtain data text fragments, wherein the interpretation template database includes at least one of the following: detailed information template, status description template, year-on-year description template, quarter-on-quarter description template, competition results template, competition experience template, reward and commendation template, and punishment warning template.

[0117] In an optional embodiment, the type of student information synthesizer includes at least one of the following: a test score synthesizer, a classroom performance synthesizer, and a comprehensive performance synthesizer, and synthesizing data text segments into an electronic document based on the student information synthesizer includes: reading target data in a student information database based on the student information synthesizer; calling the student information interpreter in sequence based on the target data to generate data text segments corresponding to the target data; when it is recognized that the student information interpreter has completed the task of generating data text segments, synthesizing the data text segments corresponding to the target data in a preset order to obtain an electronic document.

[0118] In an optional embodiment, after calling the student information interpreter in sequence based on the target data to generate data text segments corresponding to the target data, the method also includes: judging whether the student information interpreter has completed the task of generating the data text segments; if it is identified that the student information interpreter has completed the generation task, executing the step of synthesizing the data text segments corresponding to the target data in a preset order to obtain an electronic document; if it is identified that the student information interpreter has not completed the generation task, repeating the step of calling the student information interpreter in sequence based on the target data to generate the data text segments corresponding to the target data.

[0119] In an optional implementation, an electronic document is converted into a large model prompt word through an evaluation prompt word generator and an evaluation template library, including: identifying user evaluation dimensions in the electronic document based on the evaluation prompt words; setting an evaluation template library corresponding to the user evaluation dimensions, and converting the electronic document into a large model prompt word based on the evaluation template library, wherein the large model prompt word includes at least one of the following: role, goal, skill, input, and output.

[0120] In an optional implementation, the evaluation template library is used to define the word count range and precautions of the electronic document, and the evaluation template library includes at least one of the following: academic performance evaluation, moral behavior evaluation, innovation ability evaluation, and comprehensive ability evaluation.

[0121] In an optional implementation, a large language model is called, and the large model prompt words are converted into a student evaluation report based on the large language model, including: calling the large language model through an application program interface; reasoning the large model prompt words based on the large language model to obtain a student evaluation report.

[0122] In an optional embodiment, the embodiment of the present application may also include a program product for implementing the above method, which may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0123] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0124] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0125] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0126] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0127] In addition, in an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.

[0128] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0129] Refer to the following Figure 6 The electronic device 600 according to this embodiment of the present application is described. Figure 6 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0130] like Figure 6 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: the at least one processing unit 610, the at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), and a display unit 640.

[0131] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps of various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification. For example, the processing unit 610 can execute the following steps: converting the student information data in the student information database through the student information interpreter to obtain data text segments; synthesizing the data text segments into electronic documents based on the student information synthesizer; converting the electronic documents into large model prompt words through the evaluation prompt word generator and the evaluation template library; calling the large language model, and converting the large model prompt words into a student evaluation report based on the large language model.

[0132] In an optional embodiment, the student information interpreter includes: an interpretation rule database, an interpretation template database, and the student information data in the student information database is converted by the student information interpreter to obtain data text fragments, including: interpreting the student information data based on the interpretation rule database to obtain interpreted student data, wherein the interpretation rule database includes at least one of the following: threshold division rules, range division rules, percentile division rules, and change ratio division rules; inputting the interpreted student data into the interpretation template database to convert the student information data to obtain data text fragments, wherein the interpretation template database includes at least one of the following: detailed information template, status description template, year-on-year description template, quarter-on-quarter description template, competition results template, competition experience template, reward and commendation template, and punishment warning template.

[0133] In an optional embodiment, the type of student information synthesizer includes at least one of the following: a test score synthesizer, a classroom performance synthesizer, and a comprehensive performance synthesizer, and synthesizing data text segments into an electronic document based on the student information synthesizer includes: reading target data in a student information database based on the student information synthesizer; calling the student information interpreter in sequence based on the target data to generate data text segments corresponding to the target data; when it is recognized that the student information interpreter has completed the task of generating data text segments, synthesizing the data text segments corresponding to the target data in a preset order to obtain an electronic document.

[0134] In an optional embodiment, after calling the student information interpreter in sequence based on the target data to generate data text segments corresponding to the target data, the method also includes: judging whether the student information interpreter has completed the task of generating the data text segments; if it is identified that the student information interpreter has completed the generation task, executing the step of synthesizing the data text segments corresponding to the target data in a preset order to obtain an electronic document; if it is identified that the student information interpreter has not completed the generation task, repeating the step of calling the student information interpreter in sequence based on the target data to generate the data text segments corresponding to the target data.

[0135] In an optional implementation, an electronic document is converted into a large model prompt word through an evaluation prompt word generator and an evaluation template library, including: identifying user evaluation dimensions in the electronic document based on the evaluation prompt words; setting an evaluation template library corresponding to the user evaluation dimensions, and converting the electronic document into a large model prompt word based on the evaluation template library, wherein the large model prompt word includes at least one of the following: role, goal, skill, input, and output.

[0136] In an optional implementation, the evaluation template library is used to define the word count range and precautions of the electronic document, and the evaluation template library includes at least one of the following: academic performance evaluation, moral behavior evaluation, innovation ability evaluation, and comprehensive ability evaluation.

[0137] In an optional implementation, a large language model is called, and the large model prompt words are converted into a student evaluation report based on the large language model, including: calling the large language model through an application program interface; reasoning the large model prompt words based on the large language model to obtain a student evaluation report.

[0138] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0139] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0140] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0141] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 660. As shown, the network adapter 660 communicates with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0142] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0143] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0144] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application. The specification and embodiments are to be regarded as exemplary only, and the true scope and spirit of the present application are indicated by the claims.

Claims

1. A comprehensive student evaluation method, characterized in that: include: The student information data in the student information database is converted by a student information interpreter to obtain data text fragments; synthesizing the data text segments into an electronic document based on a student information synthesizer; Converting the electronic document into large model prompt words through an evaluation prompt word generator and an evaluation template library; The large language model is called, and the large model prompt words are converted into a student evaluation report according to the large language model.

2. The method according to claim 1, characterized in that The student information interpreter includes: an interpretation rule database and an interpretation template database. The student information data in the student information database is converted by the student information interpreter to obtain data text segments, including: The student information data is interpreted based on the interpretation rule database to obtain the interpreted student data, wherein the interpretation rule database includes at least one of the following: a threshold division rule, a range division rule, a percentile division rule, and a change ratio division rule; The interpreted student data is input into the interpretation template database to convert the student information data to obtain data text fragments, wherein the interpretation template database includes at least one of the following: detailed information template, status description template, year-on-year description template, month-on-month description template, competition results template, competition experience template, reward and commendation template, and punishment warning template.

3. The method according to claim 1, characterized in that The type of the student information synthesizer includes at least one of the following: an examination score synthesizer, a classroom performance synthesizer, and a comprehensive performance synthesizer. The data text segments are synthesized into an electronic document based on the student information synthesizer, including: Reading target data in the student information database based on the student information synthesizer; Based on the target data, the student information interpreter is called in sequence to generate data text segments corresponding to the target data; When it is identified that the student information interpreter has completed the task of generating the data text segment, the data text segment corresponding to the target data is synthesized in a preset order to obtain the electronic document.

4. The method according to claim 3, characterized in that After sequentially calling the student information interpreter based on the target data to generate data text segments corresponding to the target data, the method further includes: Determining whether the student information interpreter has completed the task of generating the data text segment; If it is recognized that the student information interpreter has completed the generation task, the step of synthesizing the data text segments corresponding to the target data in a preset order to obtain the electronic document is performed; If it is identified that the student information interpreter has not completed the generation task, the step of calling the student information interpreter in sequence based on the target data to generate a data text segment corresponding to the target data is repeated.

5. The method according to claim 1, characterized in that The electronic document is converted into a large model prompt word through an evaluation prompt word generator and an evaluation template library, including: Identifying user evaluation dimensions in the electronic document based on the evaluation prompt words; The evaluation template library corresponding to the user evaluation dimension is set, and the electronic document is converted into the large model prompt words based on the evaluation template library, wherein the large model prompt words include at least one of the following: role, goal, skill, input, and output.

6. The method according to claim 5, characterized in that The evaluation template library is used to define the word count range and precautions of the electronic document. The evaluation template library includes at least one of the following: academic performance evaluation, moral behavior evaluation, innovation ability evaluation, and comprehensive ability evaluation.

7. The method according to claim 1, characterized in that Calling the large language model, and converting the large model prompt words into a student evaluation report according to the large language model, including: Calling the large language model through an application program interface; The large model prompt words are inferred based on the large language model to obtain the student evaluation report.

8. A comprehensive evaluation device for students, characterized in that: include: A first conversion unit is used to convert the student information data in the student information database through a student information interpreter to obtain a data text segment; A synthesis unit, for synthesizing the data text segments into an electronic document based on a student information synthesizer; A second conversion unit, configured to convert the electronic document into a large model prompt word through an evaluation prompt word generator and an evaluation template library; The calling unit is used to call the large language model and convert the large model prompt words into a student evaluation report according to the large language model.

9. A computer-readable storage medium, characterized in that: The storage medium includes a stored program, wherein the program executes the student comprehensive evaluation method described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: One or more processors, a memory, a display device, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the comprehensive student evaluation method described in any one of claims 1 to 7.

Images