Automatic detection method for installing and setting multi-language input method of translation man-machine conversation examination

Abstract

The present invention relates to the technical field of automatic input method detection, and in particular to a method for automatic detection of the installation and setting of multilingual input methods for translation human-computer dialogue examinations. The method comprises the following steps: automatically identifying and installing a language input method based on examinee information; calculating weight coefficients of test items in a basic test process based on the installed language input method and historical test information of the basic test process; analyzing abnormal information in the history of the language input method, selecting characteristic test items, automatically detecting the installed language input method based on the basic test process and the characteristic test items of the language input method, combining the post-test score with the corresponding weight coefficient, and calculating the overall test score of the language input method. The present invention can make the test more targeted, and at the same time, automatically identifying the language input method to be installed and performing the test, so that the test process of the language input method is unified, thereby reducing the impact of the language input method on the examinee.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of input method automatic detection, and particularly relates to a method for automatically detecting installation and setting of a multilingual input method for a translation man-machine conversation examination. BACKGROUND

[0002] A translation professional qualification (level) examination adopts a machine examination form, the examination involves numerous minority languages, and needs to be matched with Chinese and foreign language input methods.

[0003] The prior art CN105653056A discloses a method and device for testing an input method, comprising: calculating coordinates of each key in an input method interface according to a preset algorithm, and writing the coordinates of each key into a configuration file; starting a test program, loading and analyzing the configuration file to obtain coordinates of at least one key corresponding to a test string; simulating a click operation at a corresponding position of the input method interface according to the coordinates of the at least one key corresponding to the test string; and obtaining candidate word content and checking whether the candidate word content is correct.

[0004] However, in the process of the translation professional qualification examination, if the input methods are manually installed and tested, not only is the workload huge, but also because of the strong professional nature, general test personnel do not have relevant test knowledge, and manual testing will make the test standards of the input method test not unified, thereby affecting the examination state of the examinees. SUMMARY

[0005] The purpose of the present application is to solve the problems in the background art, and a method for automatically detecting installation and setting of a multilingual input method for a translation man-machine conversation examination is provided.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] The method for automatically detecting installation and setting of a multilingual input method for a translation man-machine conversation examination specifically comprises the following steps:

[0008] Step 1: based on a machine examination database, obtaining examinee information, matching the examinee information in the machine examination database to obtain a translation examination language corresponding to the examinee, and simultaneously matching a corresponding language input method in an input database based on the translation examination language and automatically installing the language input method;

[0009] Step 2: obtaining a basic test process of the corresponding language input method and a corresponding standard response value according to the installed language input method, and calculating a weight coefficient of a test item in the basic test process based on historical test information of the basic test process;

[0010] Step three: further obtain the abnormal information of the installed language input method history, and classify the abnormal information according to the abnormal reasons of the abnormal information, obtain the data set of each fault type in the abnormal information, process the fault occurrence data in the data set based on the fault occurrence data, and obtain the fault fluctuation value and the average delay time of each time period in the fault occurrence data, and then calculate the comprehensive influence value of the fault type based on the fault fluctuation value and the average delay time, and determine the characteristic fault of the corresponding language input method based on the comprehensive influence value;

[0011] Step four: based on the characteristic fault, determine the characteristic test item, and perform installation testing on the installed language data method according to the characteristic test item and the basic test process, and obtain the test score of the corresponding test item based on the test process, and then obtain the detection qualified signal and the detection abnormal signal based on the test score, and then calculate the test overall score of the corresponding language input method based on the detection qualified signal, the test score of the test item in the basic test process, and the test score of the characteristic test item, and finally obtain the detection completion signal based on the test overall score.

[0012] As a further scheme of the present application, the method for automatically installing the language input method comprises:

[0013] A machine test database is set, wherein the machine test database sets a test taker database and an input database, the test taker database is used for identifying test taker information in a current test, the test taker information includes an admission ticket number and a translation test language, and each admission ticket number corresponds to one translation test language, and the input database is used for storing an input method for a translation test and a corresponding additional plug-in;

[0014] An information input unit and an information matching unit are set, before the translation test starts, a test taker inputs an admission ticket number to the information input unit, the information input unit transmits the admission ticket number to the information matching unit, the information matching unit searches the test taker database with the admission ticket number to obtain a matched translation test language;

[0015] Based on the matched translation test language, the translation test language is matched in the input database to obtain a matched language input method and a plug-in, and then an installation instruction signal is automatically generated, and the matched language input method is automatically installed based on the installation instruction signal.

[0016] As a further scheme of the present application, the calculation method of the weight coefficient of the test item in the basic test process comprises:

[0017] S1: based on the test requirement information of the language input method, a plurality of basic test processes are set, wherein the basic test process includes input function testing, performance testing, shortcut key testing and word library testing;

[0018] A standard test library is set, wherein the standard test library is used to test the test items in the basic test procedure, and based on the test result, a standard response value of each test item is obtained;

[0019] S2: historical test information of a language input method is acquired, test items in the historical test information are divided according to test items in the basic test procedure, then a test item in the basic test procedure is selected at random and marked as a target item, taking the target item as an example, test data corresponding to the target item in the historical test information is acquired, and the test data is marked as CSi, wherein i=1, 2, …, I, indicating that the target item exists in I test data;

[0020] The formula is used The test data of the target item is converted into standardized data , wherein j represents a test item, and j=1, 2, …, J, indicating that there are j test items in the basic test procedure, and XBj represents a standard response value of the test item j;

[0021] S3: based on the formula The information entropy Hj of the target item j is calculated, wherein , represents a probability distribution value of the test data i in the test item j, and further ;

[0022] S4: based on the formula dj=1-Hj, the difference coefficient dj of the test item j is obtained, and the weight coefficient of the test item j is obtained by using the formula .

[0023] As a further scheme of the present application, the standard response value of the test item includes:

[0024] The basic test procedure includes input function test, performance test, shortcut key test and word library test, the standard response value of the function test refers to the accuracy rate of the input method response, the standard response value of the performance test refers to the real-time response time of the input method, the standard response value of the shortcut key test refers to the accuracy rate of the shortcut key conversion, and the standard response value of the word library test refers to the integrity of the word library.

[0025] As a further scheme of the present application, the determination method of the fault fluctuation value includes:

[0026] SS1: based on the installed language input method, abnormal information occurring when the language input method is used in a translation test is acquired, reasons corresponding to the abnormal information are acquired, the abnormal information is classified according to the reasons of the abnormal information, and a data set of the abnormal information is obtained, wherein each abnormal information corresponds to a data set;

[0027] An arbitrary fault type is selected from the abnormal information, and is marked as a target fault, taking the target fault as an example, a data set of the target fault is obtained, wherein the data set contains historical fault occurrence data of the corresponding fault type;

[0028] The data in the data set is divided according to the test time, the number of occurrences of the target fault in the same test time is counted and marked as Fm, m = 1, 2, …, M, indicating that there are M tests in total;

[0029] SS2: Obtain the total number of times YSm of installation of the corresponding language input method in each time period, and then obtain the fault occurrence probability GLm of the target fault by using the formula Fm ÷ YSm = GLm;

[0030] The fault occurrence probabilities of different time periods are processed by mean value, to obtain the fault occurrence mean value GLp, and then based on the formula The fault fluctuation value Bn of the target fault is determined, and n represents the target fault.

[0031] As a further scheme of the application, the method for determining the comprehensive influence value comprises:

[0032] Based on the occurrence data of the target fault, the fault delay time of each fault is obtained, and the fault delay times of all faults in the data set are integrated and processed by mean value to obtain the average delay time tp of the target fault;

[0033] The formula is used to calculate the comprehensive influence value YZn of the target fault, wherein, and are proportional factors, and a1 and a2 are base coefficients.

[0034] As a further scheme of the application, the method for determining the characteristic fault comprises:

[0035] An influence threshold Yy is obtained, the comprehensive influence values YZn of each fault type are compared with the influence threshold Yy respectively, and the fault type with the comprehensive influence value YZn greater than or equal to the influence threshold Yy is taken as a characteristic fault.

[0036] As a further scheme of the application, the method for determining the detection qualified signal comprises:

[0037] The characteristic fault is taken as the characteristic test item of the language input method in the present translation test, the installation test of the language input method after automatic installation is carried out based on the basic test process and the characteristic test item, and further, the test score is set in each test procedure, the test score is used for score evaluation of each test item, wherein the higher the score of the test item is, the higher the running stability of the corresponding test item is, and vice versa, the lower the score of the test item is, the lower the running stability of the corresponding test item is;

[0038] When the installation test is completed, the test scores of all test items are obtained, and the test score of the basic test process is marked as PCj, and the test score of the characteristic test item is marked as PTe, e = 1, 2, …, E, indicating that there are E characteristic test items of the corresponding language input method in the present test;

[0039] The test scores of all test items are compared with the test passing scores of the corresponding test items respectively, if the test scores of all test items are greater than or equal to the test passing scores of the corresponding test items, a test qualified signal is generated.

[0040] As a further scheme of the present application, when the test score of the test item is less than the test passing score, a test abnormal signal is generated, and the corresponding test item and the test abnormal signal are transmitted to the display terminal at the same time, and an audible and light reminding signal is generated to remind the corresponding responsible personnel, and the corresponding test item is maintained by the responsible personnel, and when the maintenance is completed, the installation test of the corresponding test item is carried out again until the test qualified signal is generated.

[0041] As a further scheme of the present application, the generation method of the test completion signal comprises:

[0042] When the test qualified signal is generated, the test overall score Zf is calculated by the formula The weight coefficient of the test item j in the basic test process is represented by PCj;

[0043] The test overall score Zf is compared with the overall test threshold, if the test overall score Zf is greater than or equal to the overall test threshold, a test completion signal is generated and transmitted to the terminal equipment, otherwise, if the test overall score Zf is less than the overall test threshold, an input lag signal is generated and transmitted to the display terminal, and then when the corresponding responsible personnel obtains the input lag signal, the corresponding language input method is adjusted.

[0044] Compared with the prior art, the present application has the following advantages:

[0045] ​The present application can accurately reflect the problems in the basic test process of the input method by analyzing the weight of the test items in the basic test process of different input methods based on the installed language input method, and can improve the test efficiency and accuracy by analyzing the historical abnormal information of the installed language input method, selecting the corresponding feature fault, and determining the feature test item based on the feature fault.

[0046] The present application can accurately reflect the problems in the basic test process of the input method by analyzing the weight of the test items in the basic test process of different input methods based on the installed language input method, and can improve the test efficiency and accuracy by analyzing the historical abnormal information of the installed language input method, selecting the corresponding feature fault, and determining the feature test item based on the feature fault. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 The present application is a method flow structure diagram. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all.

[0049] Referring to Figure 1 , the automatic detection method for multi-language input method installation and setting of the translation man-machine dialogue test, which specifically includes the following steps:

[0050] Step 1: Set up a computer test database, wherein the computer test database sets up a candidate database and an input database, further, the candidate database is used to identify the candidate information in the current test, the candidate information includes an admission ticket number and a translation test language, and each admission ticket number corresponds to a translation test language, and the input database is used to store the input method of the translation test and the corresponding additional plug-in;

[0051] Set up an information input unit and an information matching unit, before the translation test starts, the candidate inputs the admission ticket number into the information input unit, the information input unit transmits the admission ticket number to the information matching unit, and the information matching unit searches the candidate database with the admission ticket number to obtain the matched translation test language;

[0052] Based on the matched translation test language, the translation test language is matched in the input database to obtain the matched language input method and plug-in, and then installation instruction signals are automatically generated, and the matched language input method is automatically installed based on the installation instruction signals;

[0053] Step two: after the language input method is automatically installed, based on the translation test language corresponding to the language input method, the test requirement information of the language is collected, and then based on the test requirement information, a weight factor is set for the basic test process, and the specific setting method includes:

[0054] S1: based on the test requirement information of the language input method, a plurality of basic test processes are set, wherein the basic test processes include input function test, performance test, shortcut key test and word library test;

[0055] Then a standard test library is set, wherein the standard test library is used to test the test items in the basic test process, and based on the test results, the standard response value of each test item is obtained, wherein the standard response value of the function test refers to the accuracy of the input method response, the standard response value of the performance test refers to the real-time response time of the input method, the standard response value of the shortcut key test refers to the accuracy of the shortcut key conversion, and the standard response value of the word library test refers to the integrity of the word library;

[0056] S2: obtain the historical test information of the language input method, divide the test items in the historical test information according to the test items in the basic test process, then select a test item in the basic test process at random and mark it as a target item, and take the target item as an example, obtain the test data corresponding to the target item in the historical test information, and mark the test data as CSi, wherein i=1, 2, …, I, indicating that there are I test data for the target item;

[0057] Use the formula to convert the test data of the target item into standardized data , wherein j represents the test item, and j=1, 2, …, J, indicating that there are j test items in the basic test process, and XBj represents the standard response value of the test item j;

[0058] S3: based on the formula , the information entropy Hj of the target item j is calculated, wherein , represents the probability distribution value of the test data i in the test item j, and further ;

[0059] Then the remaining test items in the basic test process are taken as the target item in turn, and the above steps S2 and S3 are processed according to the above steps S2 and S3 to obtain the information entropy Hj of each test item j.

[0060] S4: obtaining the difference coefficient dj of the test item j based on the formula dj = 1-Hj, and then obtaining the weight coefficient of the test item j by using the formula ;

[0061] Step three: based on the installed language input method, obtaining the abnormal information occurred in the translation test of the language input method, and obtaining the corresponding reasons of the abnormal information, and classifying the abnormal information according to the reasons of the abnormal information to obtain a data set of the abnormal information, wherein each abnormal information corresponds to a data set, and then analyzing the data set of the abnormal information to determine the characteristic fault, and further, the specific determination method of the characteristic fault includes:

[0062] SS1: randomly selecting a fault type in the abnormal information and marking it as a target fault, taking the target fault as an example, obtaining the data set of the target fault, wherein the data set contains historical fault occurrence data corresponding to the fault type;

[0063] Divide the data in the data set according to the test time, and count the number of target fault occurrences in the same test time and mark it as Fm, m = 1, 2, …, M, indicating that there are M tests in total;

[0064] SS2: obtaining the total number of times YSm of installing the corresponding language input method in each time period, and then obtaining the fault occurrence probability GLm of the target fault by using the formula Fm ÷ YSm = GLm;

[0065] Perform mean value processing on the fault occurrence probabilities of different time periods to obtain the fault occurrence mean value GLp, and then determine the fault fluctuation value Bn of the target fault based on the formula ;

[0066] Based on the occurrence data of the target fault, obtaining the fault delay time of each fault, and then comprehensively processing and performing mean value processing on the fault delay time of all faults in the data set to obtain the average delay time tp of the target fault;

[0067] SS3: calculating the comprehensive influence value YZn of the target fault by using the formula ; and are proportional factors, a1 and a2 are base coefficients respectively, and specifically , , a1 and a2 are obtained by big data operation by those skilled in the art;

[0068] It needs to be further explained that the greater the comprehensive influence value of the target fault is, the greater the influence of the target fault on the examinee is, and vice versa, the smaller the comprehensive influence value of the target fault is, the smaller the influence of the target fault on the examinee is;

[0069] After that, the remaining fault types in the abnormal information are sequentially taken as target faults, and the method in the above steps SS1 to SS3 is used for processing to obtain the comprehensive influence value YZn of each fault type respectively;

[0070] SS4: Obtain the influence threshold Yy, compare the comprehensive influence value YZn of each fault type with the influence threshold Yy respectively, take the fault type whose comprehensive influence value YZn is greater than or equal to the influence threshold Yy, and mark it as a characteristic fault, wherein the specific value of the influence threshold Yy is obtained by the technical personnel in the art through big data operation;

[0071] Step four: taking the characteristic fault as a characteristic test item of the corresponding language input method in this translation test, based on the basic test process and the characteristic test item, the language input method after automatic installation is tested, and further, a test score is set in each test program, which is used for score evaluation of each test item, wherein the higher the score of the test item is, the higher the running stability of the corresponding test item is, and vice versa, the lower the score of the test item is, the lower the running stability of the corresponding test item is, and the specific setting of the test score in the test program is set by the technical personnel in the art according to big data experience;

[0072] When the installation test is completed, the test scores of all test items are obtained, and the test score of the basic test process is marked as PCj, and the test score of the characteristic test item is marked as PTe, e=1, 2, …, E, indicating that there are E characteristic test items of the corresponding language input method in this test;

[0073] First, compare the test scores of all test items with the test passing scores of the corresponding test items respectively, if the test scores of all test items are greater than or equal to the test passing scores of the corresponding test items, a detection qualified signal is generated, otherwise, if there is a test score of a test item less than the test passing score, a detection abnormal signal is generated, and the corresponding test item and the detection abnormal signal are transmitted to the display terminal at the same time, and an audible and light reminding signal is generated to remind the corresponding responsible personnel, and the corresponding responsible personnel maintains the corresponding test item, and when the fault maintenance is completed, the corresponding test item is re-installed and tested until the installation test generates a detection qualified signal;

[0074] When the detection qualified signal is generated, the formula The test overall score Zf is calculated, and then compared with the overall test threshold value. If the test overall score Zf is greater than or equal to the overall test threshold value, a detection completion signal is generated and transmitted to the terminal device. Otherwise, if the test overall score Zf is less than the overall test threshold value, an input lag signal is generated and transmitted to the display terminal. Then, when the corresponding responsible person obtains the input lag signal, the corresponding language input method is adjusted, thereby reducing the influence of the language input method on the examinee.

[0075] It should be further explained that the test passing score of the test item and the specific value of the overall test threshold value are set by the person skilled in the art according to big data experience.

[0076] The above is only a preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art, within the technical range disclosed by the present application, according to the technical solution and the inventive concept of the present application, makes equivalent replacement or changes, which should be covered within the protection scope of the present application.

Claims

1. A method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test, characterized in that: The method specifically comprises the following steps: Step 1: Based on the computer-based test database, obtain the candidate information, match the candidate information with the computer-based test database, obtain the corresponding candidate's translated test language, and based on the translated test language, match the corresponding language input method in the input database and automatically install it; Step 2: Obtain the basic test process and corresponding standard response value of the language input method according to the installed language input method, and calculate the weight coefficients of the test items in the basic test process based on the historical test information of the basic test process; Step 3: Obtain historical exception information of the installed language input method and classify the exception information according to the cause of the exception information to obtain a data set for each fault type in the exception information. Based on the fault occurrence data in the data set, process the number of fault occurrences and fault delay time in each time period of the fault occurrence data to obtain the fault fluctuation value and average delay time. Then, calculate the comprehensive impact value of the fault type based on the fault fluctuation value and average delay time. Based on the comprehensive impact value, determine the characteristic fault of the corresponding language input method; The method for determining the fault fluctuation value includes: SS1: Based on the installed language input method, obtain the exception information that occurs during the translation test for this language input method, and simultaneously obtain the cause corresponding to the exception information. Then, classify the exception information according to the cause of the exception information to obtain a data set of the exception information, where each exception information corresponds to a data set; Randomly select a fault type from the abnormal information and mark it as a target fault. Taking the target fault as an example, obtain a data set of the target fault, where the data set contains historical fault occurrence data of the corresponding fault type; The data in the data set are divided according to the test time, and the number of target faults occurring within the same test time is counted and marked as Fm, where m = 1, 2, ..., M, indicating that there are M tests in total; SS2: Obtain the total number of language input method installations YSm in each time period, and then use the formula Fm ÷ YSm = GLm to obtain the probability of occurrence of the target fault GLm; The fault occurrence probability of different time periods is processed by averaging to obtain the fault occurrence mean GLp, and then based on the formula Determine the fault fluctuation value Bn of the target fault, where n represents the target fault; Step 4: Based on the characteristic fault, determine the characteristic test items, perform installation test on the installed language data method according to the characteristic test items and the basic test process, and obtain the test scores of the corresponding test items based on the test process. According to the test scores, first obtain the detection pass signal and the detection abnormality signal, and then based on the detection pass signal, combine the test scores of the test items in the basic test process with the corresponding weight coefficients and the test scores of the characteristic test items to calculate the overall test score of the corresponding language input method, and finally obtain the detection completion signal based on the overall test score.

2. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 1, characterized in that: Methods for automatically installing language input methods include: Setting up a computer-based test database, wherein a candidate database and an input database are set up in the computer-based test database. The candidate database is used to identify the candidate information of the current test, and the candidate information includes the admission ticket number and the translation test language, and each admission ticket number corresponds to a translation test language. The input database is used to store the input method of the translation test and the corresponding additional plug-ins; An information input unit and an information matching unit are provided. Before the translation test begins, the candidate inputs the admission ticket number into the information input unit, which transmits the admission ticket number to the information matching unit. The information matching unit searches the candidate database for the admission ticket number to obtain a matching translation test language. Based on the matched translation test language, the translation test language is language matched in the input database to obtain a matching language input method and plug-in, and then an installation instruction signal is automatically generated, and the matched language input method is automatically installed based on the installation instruction signal.

3. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 1, characterized in that: The calculation method of the weight coefficient of the test items in the basic test process includes: S1: Based on the language input method test requirements, multiple basic test processes are set up, including input function test, performance test, shortcut key test, and vocabulary test; Setting up a standard test library, wherein the standard test library is used to test the test items in the basic test process and obtain a standard response value for each test item based on the test results; S2: Obtain historical test information of the language input method, divide the test items in the historical test information into the test items in the basic test process, then arbitrarily select a test item in the basic test process and mark it as a target item. Taking the target item as an example, obtain the test data corresponding to the target item in the historical test information and mark the test data as CSi, where i = 1, 2, ..., 1, indicating that there are I test data for the target item; Using the formula Convert the target project's test data into standardized data , where j represents the test item, and j=1, 2, ..., J, indicating that there are J test items in the basic test process, and XBj represents the standard response value of test item j; S3: Formula-based The information entropy Hj of test item j is calculated, where , represents the probability distribution value of test data i in test item j. Further, ; S4: Based on the formula dj=1-Hj, the difference coefficient dj of test item j is obtained, and then the formula Get the weight coefficient of test item j.

4. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 3, characterized in that: Standard response values ​​for test items include: The basic testing process includes input function testing, performance testing, shortcut key testing and vocabulary testing. The standard response value of the function test refers to the accuracy of the input method response, the standard response value of the performance test refers to the real-time response time of the input method, the standard response value of the shortcut key test refers to the accuracy of the shortcut key conversion, and the standard response value of the vocabulary test refers to the integrity of the vocabulary.

5. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 1, characterized in that: Methods for determining the comprehensive impact value include: Based on the occurrence data of the target fault, the fault delay time of each fault is obtained. At the same time, the fault delay time of all faults in the data set is integrated and averaged to obtain the average delay time tp of the target fault; Using the formula Calculate the comprehensive impact value YZn of the target fault, where: and are all proportional factors, a1 and a2 are base coefficients respectively.

6. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 5, characterized in that: Methods for determining characteristic faults include: Obtain the impact threshold Yy, compare the comprehensive impact value YZn of each fault type with the impact threshold Yy respectively, select the fault type with a comprehensive impact value YZn greater than or equal to the impact threshold Yy, and mark it as a characteristic fault.

7. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 1, characterized in that: Methods for determining a qualified detection signal include: Characteristic faults are used as characteristic test items for the corresponding language input method in this translation test. Based on the basic test process and characteristic test items, the language input method after automatic installation is installed and tested. Furthermore, a test score is set in each test program. The test score is used to score each test item. The higher the score of the test item, the higher the running stability of the corresponding test item. Conversely, the lower the score of the test item, the lower the running stability of the corresponding test item. After the installation test is completed, the test scores of all test items are obtained. The test scores of the basic test process are marked as PCj, and the test scores of the feature test items are marked as PTe, where e = 1, 2, ..., E, indicating that the corresponding language input method has E feature test items in this test. The test scores of all test items are compared with the test passing scores of the corresponding test items. If the test scores of all test items are greater than or equal to the test passing scores of the corresponding test items, a detection pass signal is generated.

8. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 7, characterized in that: When the test score of a test item is less than the passing score, a detection abnormality signal is generated, and the corresponding test item and the detection abnormality signal are simultaneously transmitted to the display terminal, and an audible and visual reminder signal is generated to remind the corresponding responsible personnel, who then perform fault maintenance on the corresponding test item. After the fault maintenance is completed, the corresponding test item is reinstalled and tested until the installation test generates a detection pass signal.

9. The method for automatically detecting the installation and setting of a multilingual input method for a translation human-computer dialogue test according to claim 7, characterized in that: The method for generating the detection completion signal includes: When a qualified detection signal is generated, the formula Calculate the overall test score Zf, Represents the weight coefficient of test item j in the basic test process; The overall test score Zf is compared with the overall test threshold. If the overall test score Zf is greater than or equal to the overall test threshold, a detection completion signal is generated and transmitted to the terminal device. Conversely, if the overall test score Zf is less than the overall test threshold, an input jam signal is generated and transmitted to the display terminal. When the corresponding responsible personnel obtains the input jam signal, the corresponding language input method is adjusted.

Images