CN104809062A - Test method and system of artificial intelligence answering system - Google Patents
Test method and system of artificial intelligence answering system Download PDFInfo
- Publication number
- CN104809062A CN104809062A CN201510193639.0A CN201510193639A CN104809062A CN 104809062 A CN104809062 A CN 104809062A CN 201510193639 A CN201510193639 A CN 201510193639A CN 104809062 A CN104809062 A CN 104809062A
- Authority
- CN
- China
- Prior art keywords
- session
- scene
- artificial intelligence
- current sessions
- conversation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses a test method and system of an artificial intelligence answering system. The method comprises the following steps that a conversation set of a plurality of conversation elements is obtained, and the conversation elements are conversation or scene ending marks; a conversation scene generating step comprises the processes of sequentially taking out conversation elements from the conversation set to be used as the current conversation elements and creating the conversation scene; the question included in the current conversation element is input into the artificial intelligence answering system in the conversation scene, and the actual answer of the artificial intelligence answering system for responding to the question is grabbed; a next conversation element is taken out from the conversation set in sequence, if the current conversation element is the conversation, the conversation test step is executed, otherwise, the conversation scene is ended, if a next conversation element also exists in the conversation set, the conversation scene generating step is executed, and otherwise, the operation is ended. The method and the system have the advantage that the coverage on multi-scene multi-user and complicated-premise-requirement test requirements can be realized.
Description
Technical field
The present invention relates to artificial intelligence correlative technology field, particularly a kind of method of testing of artificial intelligence response system and system.
Background technology
Artificial intelligence is the application for natural language processing, the content that the test of artificial intelligence will be paid close attention to and traditional automatic test inconsistent, particularly the web of artificial intelligence response system is applied, except page function, a main test emphasis be corresponding input problem whether can to corresponding result, for the variation of natural language and the instability of model adjustment, test needs to carry out a large amount of recurrence checkings, wastes a large amount of manpowers and time.
Prior art adopts following mode to complete automatic test corresponding to artificial intelligence response system:
Use based on the automated test tool of increasing income of Google: selenium operates web page, complete and put question to and answer, the preservation content of input results only comprises problem and answer, in next session operation of complete rear direct execution, and by outcome record.Outcome record content only comprises problem and actual result.
The shortcoming of prior art:
(1) problem result can because contextual content enters different scenes thus causes subproblem not enter correct treatment scheme, and result accuracy is inadequate.
(2) once execution can only cover a kind of use scenes, not easily switches, need multiple exercise guarantee to reach the effect of many scenes to different scenes in scene performs.
(3) session data sequential organization is indefinite, lacks actuating logic.
(4) execution result preserves imperfection, only the result of correspondence is exported and preserves, not easily carry out data statistics and maintenance.
Summary of the invention
Based on this, be necessary for the inadequate technical matters of prior art test accuracy, a kind of method of testing and system of artificial intelligence response system are provided.
A method of testing for artificial intelligence response system, comprising:
Session aggregation obtaining step, comprise: obtain the session aggregation comprising multiple session element, described session element is that session or scene terminate mark, the session element that described session aggregation comprises at least one for scene terminate mark, each described session comprises: problem, scene identity and expection answer;
Session context generation step, comprising: from described session aggregation, take out session element in order as current sessions element, if current sessions element is session, then create session context;
Conversation test step, comprise: to the problem included by artificial intelligence response system input current sessions element in session context, capture the actual answer of problem described in described artificial intelligence response system responses, if actual answer and the expection answer matches included by current sessions element, then record the test result of current sessions element for passing through, otherwise the test result of record current sessions element is unsuccessfully;
Session element checks step, comprise: from session aggregation, take out next session element in order as current sessions element, mark is terminated if current sessions element is scene, then end session scene, perform and terminate to check step, if current sessions element is session, then perform described conversation test step;
Terminate to check step, comprising: if also have next session element in session aggregation, then perform session context generation step, otherwise terminate.
A test macro for artificial intelligence response system, comprising:
Session aggregation acquisition module, for: obtain the session aggregation comprising multiple session element, described session element is that session or scene terminate mark, the session element that described session aggregation comprises at least one for scene terminate mark, each described session comprises: problem, scene identity and expection answer;
Session context generation module, for: from described session aggregation, take out session element in order as current sessions element, if current sessions element is session, then create session context;
Conversation test module, for: to the problem included by artificial intelligence response system input current sessions element in session context, capture the actual answer of problem described in described artificial intelligence response system responses, if actual answer and the expection answer matches included by current sessions element, then record the test result of current sessions element for passing through, otherwise the test result of record current sessions element is unsuccessfully;
Session element checking module, for: from session aggregation, take out next session element in order as current sessions element, mark is terminated if current sessions element is scene, then end session scene, perform and terminate checking module, if current sessions element is session, then perform described conversation test module;
Terminate checking module, for: if also have next session element in session aggregation, then perform session context generation module, otherwise terminate.
The present invention increases scene terminate to identify and relevant flow process by concentrating in session, makes test automatically can tackle the situation of multiple scene in once complete test, can cover the testing requirement of many scenes, multi-user and complicated premise calls.
Accompanying drawing explanation
Fig. 1 is the workflow diagram of the method for testing of a kind of artificial intelligence response system of the present invention;
Fig. 2 is the workflow diagram of preferred embodiment;
Fig. 3 is the construction module figure of the test macro of a kind of artificial intelligence response system of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention will be further described in detail.
Be illustrated in figure 1 the workflow diagram of the method for testing of a kind of artificial intelligence response system of the present invention, comprise:
Step S101, comprise: obtain the session aggregation comprising multiple session element, described session element be session or scene terminate mark, the session element that described session aggregation comprises at least one for scene terminate identify, each described session comprises: problem, scene identity and expection answer;
Step S102, comprising: from described session aggregation, take out session element in order as current sessions element, if current sessions element is session, then create session context;
Step S103, comprise: to the problem included by artificial intelligence response system input current sessions element in session context, capture the actual answer of problem described in described artificial intelligence response system responses, if actual answer and the expection answer matches included by current sessions element, then record the test result of current sessions element for passing through, otherwise the test result of record current sessions element is unsuccessfully;
Step S104, comprising: from session aggregation, take out next session element in order as current sessions element, terminates mark if current sessions element is scene, then end session scene, perform step S105, if current sessions element is session, then perform described step S103;
Step S105, comprising: if also have next session element in session aggregation, then perform step S102, otherwise terminate.
The present invention obtains session aggregation by step S101, include session and scene in session aggregation and terminate mark, simultaneously, create session context in step s 102, and in step S104, terminate mark if current sessions element is scene, then end session scene, thus the differentiation that can realize different sessions scene, the testing requirement of many scenes, multi-user, complicated premise calls can be covered, avoid response logic to be subject to contextual impact.
Wherein, in step s 102, if the session element taken out is not session, then can be ignored.
Wherein in an embodiment, described establishment session context is for logging in browser, and described end session scene is for closing browser.
The present embodiment to scenery control mainly for the independence ensureing current sessions scene in the cookies by refreshing current sessions scene.The present invention when processing by want scene set terminate mark, program or script is allowed to recognize, when test proceeds to this some time, represent that all sessions of this scene finish, need to upgrade the cookies of current sessions, or old cookies is cleared up, a new session context (session) when ensureing next session, can be entered.The mode the present embodiment upgrading session adopts closes browser realization.
Log in browser when performing step S102, and when performing step S104, terminate mark if current sessions element is scene, then close browser, thus the cookies of session context is upgraded.
Preferably, when performing session start, the mark that a scene starts can being set, such as a variable EndFlage, when performing initialization (or when new scene starts), being set to value, such as a False.When entering a scene, start to conversate by triggering the action logging in browser, when complete current session, next session will be taken out from queue, judge that the scene whether this session content comprises setting terminates mark, if do not comprised, then by the contents extraction of this session, perform.If find that comprising scene terminates mark, then EndFlage is set to True, program will close browser according to this EndFlage.Thus complete a complete scene.
Such flow process guarantees to perform session in the environment do not disturbed by context at, thus reaches distinctive test purpose targetedly.
Wherein in an embodiment, described session also comprises the account information associated with scene identity, and in described step S103, adopting described account information to log in described artificial intelligence should system.
In general, automatic test comprises multiple test case, and each test case completes one or session.Pass through the present invention, make the test case of automatic test can comprise multiple test scene, and by account information is associated with scene identity, then can adopt different account information for different session contexts, thus accomplish that test process is driven test case by data completely.
Wherein in an embodiment, described session aggregation adopts the mode of form to carry out test data and preserves, and wherein every data line is a session element.
In the test based on artificial intelligence response system, need to carry out test data support by a large amount of language materials, the present embodiment manages test data in order to convenient, the mode that have employed form is carried out test data and is preserved, preservation form is split with behavior unit, and data line is a session element.Different lines data represent different session informations.
Wherein in an embodiment, described step S103, also comprises: newly-generated result object, the test result of current sessions element is write described result object and preserves.
In the present embodiment, after grabbing corresponding actual answer, at once expection answer and actual answer are contrasted, thus obtain test result.Owing to directly carrying out contrasting and preserving after completing crawl, thus ensure the validity of result.Meanwhile, owing to saving test result in result object, therefore can definitely and effectively when follow-up Output rusults is shown, analyticity strengthens.
Be illustrated in figure 2 the workflow diagram of preferred embodiment, comprise:
Step S201, reads session aggregation.
Session aggregation comprises multiple session element, and session element can be that session or scene terminate mark.The preserving type of each session is as shown in table 1.
The preserving type of table 1 session
| Problem | Scene identity | Test account | Expection answer |
In addition in order to distinguish different scenes, can add the end of the invalid session tokens scene of a tape identification in test session set, namely scene terminates mark, and as shown in table 2 is the data framework of session aggregation.
The data framework of table 2 session aggregation
| Problem | Scene identity | Test account | Expection answer |
| Problem | Scene identity | Test account | Expection answer |
| Scene terminates mark | Empty | Empty | Empty |
| Problem | Scene identity | Test account | Expection answer |
| Problem | Scene identity | Test account | Expection answer |
Before performing script or flow process, the first step test data can be kept at the form of queue the data of often going in internal memory with one independently object be stored in session list, and in the mode of poll, the data of corresponding row are added session queue successively.Make session can form the list of session in a certain order.The execution that aspect is follow-up.The easily handling dirigibility that ensure that digital independent of queuing data, can enter operation to session data easily.
In order to simplify maintenance cost, here in actual treatment, the session of Same Scene will only have the Article 1 session packet of each scene containing scene identity and account information.Follow-uply will no longer to change.Occur until scene terminates mark.
Can read all sessions in the mode of poll to extract, and pass through the access characteristics of queue (List), the directly corresponding session identified of access, ensures the operability of data on other occasions.
Step S202, generates new session context (Session).
Preferably, new session is generated by logging in browser.
Step S203, to artificial intelligence response system input problem.
Step S204, captures the actual answer that artificial intelligence response system returns.
Step S205, obtain actual answer with expection answer contrast after comparing result.
After having captured the content of correspondence, the expection answer of correspondence and the actual actual answer obtained are contrasted, for comprise in actual answer expection answer or with expection answer on all four situation, be labeled as Pass (expression is passed through) then can to the test result of this session, if actual answer does not comprise or be not equal to completely expection answer, be Fail (represent and do not pass through) can to this conversation test result queue.
Step S206, preserves test result.
After complete result verification, by the test result of correspondence write result document.And then perform session next time and read, after each session performs and verifies, the content of session generates a result object, and to be write direct destination file by wiring method by this result object, preserves.
Step S207, if scene end point then performs step S208, otherwise performs step S203.
Terminate mark if the session element read is scene, be then judged as scene end point, otherwise be judged as also being less than scene end point;
Step S208, closes current session.
The closedown of current session is realized by closing browser.
Step S209, if also comprise next session in session aggregation, then performs step S202, otherwise performs step S210.
Step S210, preserves net result.
After complete all sessions, can finally preserve once result, finally can by reading result document or the interpretation of result carrying out next step.In order to easy analysis result object at least comprises content as shown in table 3.
The content of table 3 result object
| Problem | Expection answer | Actual answer | Test result |
Be illustrated in figure 3 the construction module figure of the test macro of a kind of artificial intelligence response system of the present invention, comprise:
Session aggregation acquisition module 301, for: obtain the session aggregation comprising multiple session element, described session element is that session or scene terminate mark, the session element that described session aggregation comprises at least one for scene terminate mark, each described session comprises: problem, scene identity and expection answer;
Session context generation module 302, for: from described session aggregation, take out session element in order as current sessions element, if current sessions element is session, then create session context;
Conversation test module 303, for: to the problem included by artificial intelligence response system input current sessions element in session context, capture the actual answer of problem described in described artificial intelligence response system responses, if actual answer and the expection answer matches included by current sessions element, then record the test result of current sessions element for passing through, otherwise the test result of record current sessions element is unsuccessfully;
Session element checking module 304, for: from session aggregation, take out next session element in order as current sessions element, mark is terminated if current sessions element is scene, then end session scene, perform and terminate checking module 305, if current sessions element is session, then perform described conversation test module 303;
Terminate checking module 305, for: if also have next session element in session aggregation, then perform session context generation module 302, otherwise terminate.
Wherein in an embodiment, described establishment session context is for logging in browser, and described end session scene is for closing browser.
Wherein in an embodiment, described session also comprises the account information associated with scene identity, and in described conversation test module, adopting described account information to log in described artificial intelligence should system.
Wherein in an embodiment, described session aggregation adopts the mode of form to carry out test data and preserves, and wherein every data line is a session element.
Wherein in an embodiment, described conversation test module, also comprises: newly-generated result object, the test result of current sessions element is write described result object and preserves.
The above embodiment only have expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but therefore can not be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. a method of testing for artificial intelligence response system, is characterized in that, comprising:
Session aggregation obtaining step, comprise: obtain the session aggregation comprising multiple session element, described session element is that session or scene terminate mark, the session element that described session aggregation comprises at least one for scene terminate mark, each described session comprises: problem, scene identity and expection answer;
Session context generation step, comprising: from described session aggregation, take out session element in order as current sessions element, if current sessions element is session, then create session context;
Conversation test step, comprise: to the problem included by artificial intelligence response system input current sessions element in session context, capture the actual answer of problem described in described artificial intelligence response system responses, if actual answer and the expection answer matches included by current sessions element, then record the test result of current sessions element for passing through, otherwise the test result of record current sessions element is unsuccessfully;
Session element checks step, comprise: from session aggregation, take out next session element in order as current sessions element, mark is terminated if current sessions element is scene, then end session scene, perform and terminate to check step, if current sessions element is session, then perform described conversation test step;
Terminate to check step, comprising: if also have next session element in session aggregation, then perform session context generation step, otherwise terminate.
2. the method for testing of artificial intelligence response system according to claim 1, is characterized in that, described establishment session context is for logging in browser, and described end session scene is for closing browser.
3. the method for testing of artificial intelligence response system according to claim 1, is characterized in that, described session also comprises the account information associated with scene identity, and in described conversation test step, adopting described account information to log in described artificial intelligence should system.
4. the method for testing of artificial intelligence response system according to claim 1, is characterized in that, described session aggregation adopts the mode of form to carry out test data and preserves, and wherein every data line is a session element.
5. the method for testing of artificial intelligence response system according to claim 1, is characterized in that, described conversation test step, also comprises: newly-generated result object, the test result of current sessions element is write described result object and preserves.
6. a test macro for artificial intelligence response system, is characterized in that, comprising:
Session aggregation acquisition module, for: obtain the session aggregation comprising multiple session element, described session element is that session or scene terminate mark, the session element that described session aggregation comprises at least one for scene terminate mark, each described session comprises: problem, scene identity and expection answer;
Session context generation module, for: from described session aggregation, take out session element in order as current sessions element, if current sessions element is session, then create session context;
Conversation test module, for: to the problem included by artificial intelligence response system input current sessions element in session context, capture the actual answer of problem described in described artificial intelligence response system responses, if actual answer and the expection answer matches included by current sessions element, then record the test result of current sessions element for passing through, otherwise the test result of record current sessions element is unsuccessfully;
Session element checking module, for: from session aggregation, take out next session element in order as current sessions element, mark is terminated if current sessions element is scene, then end session scene, perform and terminate checking module, if current sessions element is session, then perform described conversation test module;
Terminate checking module, for: if also have next session element in session aggregation, then perform session context generation module, otherwise terminate.
7. the test macro of artificial intelligence response system according to claim 6, is characterized in that, described establishment session context is for logging in browser, and described end session scene is for closing browser.
8. the test macro of artificial intelligence response system according to claim 6, is characterized in that, described session also comprises the account information associated with scene identity, and in described conversation test module, adopting described account information to log in described artificial intelligence should system.
9. the test macro of artificial intelligence response system according to claim 6, is characterized in that, described session aggregation adopts the mode of form to carry out test data and preserves, and wherein every data line is a session element.
10. the test macro of artificial intelligence response system according to claim 6, is characterized in that, described conversation test module, also comprises: newly-generated result object, the test result of current sessions element is write described result object and preserves.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510193639.0A CN104809062B (en) | 2015-04-22 | 2015-04-22 | A kind of method of testing and system of artificial intelligence response system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510193639.0A CN104809062B (en) | 2015-04-22 | 2015-04-22 | A kind of method of testing and system of artificial intelligence response system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104809062A true CN104809062A (en) | 2015-07-29 |
| CN104809062B CN104809062B (en) | 2017-12-01 |
Family
ID=53693904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510193639.0A Active CN104809062B (en) | 2015-04-22 | 2015-04-22 | A kind of method of testing and system of artificial intelligence response system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104809062B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503242A (en) * | 2016-11-08 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent interactive method, device and server |
| CN107402878A (en) * | 2016-05-19 | 2017-11-28 | 北京京东尚科信息技术有限公司 | Method of testing and device |
| CN107463640A (en) * | 2017-07-19 | 2017-12-12 | 安徽拓通信科技集团股份有限公司 | Artificial intelligence based information data acquisition method |
| CN108763068A (en) * | 2018-05-15 | 2018-11-06 | 福建天泉教育科技有限公司 | A kind of automated testing method and terminal based on machine learning |
| CN109656799A (en) * | 2017-10-10 | 2019-04-19 | 北京京东尚科信息技术有限公司 | Test method and device |
| CN110399469A (en) * | 2018-04-23 | 2019-11-01 | 中国电信股份有限公司 | Customer service robot understands performance detection fusion method and apparatus |
| CN110908919A (en) * | 2019-12-02 | 2020-03-24 | 上海市软件评测中心有限公司 | Response test system based on artificial intelligence and application thereof |
| CN111198823A (en) * | 2020-01-10 | 2020-05-26 | 北京声智科技有限公司 | Multi-round session testing method, device, equipment and medium |
| CN111831537A (en) * | 2019-04-18 | 2020-10-27 | 天津市元坤科技发展有限公司 | High-efficiency performance test method for artificial intelligence development system |
| CN111988195A (en) * | 2019-05-24 | 2020-11-24 | 北京京东尚科信息技术有限公司 | Response scheme determination method, device, equipment and medium for packet test |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1744056A (en) * | 2004-09-04 | 2006-03-08 | 华为技术有限公司 | Automatic test method of application |
| US7945899B2 (en) * | 2003-06-16 | 2011-05-17 | American Megatrends, Inc. | Method and system for remote software testing |
| CN103049367A (en) * | 2011-10-11 | 2013-04-17 | 神州数码信息系统有限公司 | Automatic testing method for software |
| CN103853842A (en) * | 2014-03-20 | 2014-06-11 | 百度在线网络技术（北京）有限公司 | Automatic question and answer method and system |
| US20140245289A1 (en) * | 2013-02-28 | 2014-08-28 | Apple Inc. | Automatic remote execution of an application |
| CN104142959A (en) * | 2013-05-10 | 2014-11-12 | 中国银联股份有限公司 | Automated test device and method based on expert knowledge database |
-
2015
- 2015-04-22 CN CN201510193639.0A patent/CN104809062B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7945899B2 (en) * | 2003-06-16 | 2011-05-17 | American Megatrends, Inc. | Method and system for remote software testing |
| CN1744056A (en) * | 2004-09-04 | 2006-03-08 | 华为技术有限公司 | Automatic test method of application |
| CN103049367A (en) * | 2011-10-11 | 2013-04-17 | 神州数码信息系统有限公司 | Automatic testing method for software |
| US20140245289A1 (en) * | 2013-02-28 | 2014-08-28 | Apple Inc. | Automatic remote execution of an application |
| CN104142959A (en) * | 2013-05-10 | 2014-11-12 | 中国银联股份有限公司 | Automated test device and method based on expert knowledge database |
| CN103853842A (en) * | 2014-03-20 | 2014-06-11 | 百度在线网络技术（北京）有限公司 | Automatic question and answer method and system |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107402878B (en) * | 2016-05-19 | 2020-09-01 | 北京京东尚科信息技术有限公司 | Test method and device |
| CN107402878A (en) * | 2016-05-19 | 2017-11-28 | 北京京东尚科信息技术有限公司 | Method of testing and device |
| CN106503242B (en) * | 2016-11-08 | 2019-04-19 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent interactive method, device and server |
| CN106503242A (en) * | 2016-11-08 | 2017-03-15 | 上海智臻智能网络科技股份有限公司 | A kind of intelligent interactive method, device and server |
| CN107463640A (en) * | 2017-07-19 | 2017-12-12 | 安徽拓通信科技集团股份有限公司 | Artificial intelligence based information data acquisition method |
| CN107463640B (en) * | 2017-07-19 | 2020-12-18 | 一拓通信集团股份有限公司 | Artificial intelligence based information data acquisition method |
| CN109656799B (en) * | 2017-10-10 | 2022-06-07 | 北京京东尚科信息技术有限公司 | Test method and device |
| CN109656799A (en) * | 2017-10-10 | 2019-04-19 | 北京京东尚科信息技术有限公司 | Test method and device |
| CN110399469A (en) * | 2018-04-23 | 2019-11-01 | 中国电信股份有限公司 | Customer service robot understands performance detection fusion method and apparatus |
| CN110399469B (en) * | 2018-04-23 | 2022-02-15 | 中国电信股份有限公司 | Customer service robot understanding performance detection fusion method and device |
| CN108763068A (en) * | 2018-05-15 | 2018-11-06 | 福建天泉教育科技有限公司 | A kind of automated testing method and terminal based on machine learning |
| CN111831537A (en) * | 2019-04-18 | 2020-10-27 | 天津市元坤科技发展有限公司 | High-efficiency performance test method for artificial intelligence development system |
| CN111988195A (en) * | 2019-05-24 | 2020-11-24 | 北京京东尚科信息技术有限公司 | Response scheme determination method, device, equipment and medium for packet test |
| CN110908919A (en) * | 2019-12-02 | 2020-03-24 | 上海市软件评测中心有限公司 | Response test system based on artificial intelligence and application thereof |
| CN111198823A (en) * | 2020-01-10 | 2020-05-26 | 北京声智科技有限公司 | Multi-round session testing method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104809062B (en) | 2017-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104809062A (en) | Test method and system of artificial intelligence answering system | |
| US10235603B2 (en) | Method, device and computer-readable medium for sensitive picture recognition | |
| CN111225234B (en) | Video auditing method, video auditing device, equipment and storage medium | |
| US11379206B2 (en) | APP pushing method and device, electronic device and computer-readable storage medium | |
| CN110781784A (en) | Face recognition method, device and equipment based on double-path attention mechanism | |
| CN109194689B (en) | Abnormal behavior recognition method, device, server and storage medium | |
| CN109446173A (en) | Daily record data processing method, device, computer equipment and storage medium | |
| CN107680589A (en) | Voice messaging exchange method, device and its equipment | |
| CN111476268A (en) | Method, device, equipment and medium for training reproduction recognition model and image recognition | |
| CN111091811B (en) | Method and device for processing voice training data and storage medium | |
| CN110334570B (en) | Face recognition automatic library building method, device, equipment and storage medium | |
| CN109147769B (en) | Language identification method, language identification device, translation machine, medium and equipment | |
| CN111686450B (en) | Game play generation and running method and device, electronic equipment and storage medium | |
| CN105095069A (en) | Test method and system of artificial intelligence answering system | |
| WO2019184140A1 (en) | Vr-based application program opening method, electronic apparatus, device and storage medium | |
| CN103873654A (en) | Call content analyzing and extracting system and method | |
| CN107679560A (en) | Data transmission method, device, mobile terminal and computer-readable recording medium | |
| CN107786867A (en) | Image identification method and system based on deep learning architecture | |
| CN111161265A (en) | Animal counting and image processing method and device | |
| CN115100739B (en) | Man-machine behavior detection method, system, terminal device and storage medium | |
| CN113221601A (en) | Character recognition method, device and computer readable storage medium | |
| WO2019242156A1 (en) | Method and device for controlling application in terminal, and computer readable storage medium | |
| CN111539390A (en) | Small target image identification method, equipment and system based on Yolov3 | |
| CN110275974A (en) | Data adding method, device, terminal device and the storage medium of sample data set | |
| CN107733909B (en) | Data storage method, device, server and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |