Voice interaction product test method and device based on artificial intelligence, and product

Abstract

The invention discloses a voice interaction product test method and device based on artificial intelligence and a product, and the method comprises the steps: generating a corresponding question according to a selected question class through a first artificial intelligence large model; the questioning question is converted into questioning voice; the voice interaction product needing to be tested responds to the questioning voice and outputs corresponding answering voice; the answer voice is converted into a character answer; and evaluating the matching accuracy of the character answers and the corresponding questions by using the second artificial intelligence large model, and outputting the accuracy as a test result. The invention discloses a voice interaction product test method and device based on artificial intelligence and a product, and the method comprises the steps: generating a questioning question through a first artificial intelligence large model, evaluating the matching accuracy of a character answer and the corresponding questioning question through a second artificial intelligence large model, and outputting a test result. The system has the characteristics of high automation degree of voice interaction product testing, full testing and accurate testing effect.

Description

Technical Field

[0001] The present invention belongs to the field of voice interaction products, and in particular relates to a voice interaction product testing method, device and product based on artificial intelligence. Background Art

[0002] With the rapid development of information technology, various types of voice interaction products have been widely used, for example in education, transportation, tourism, and entertainment. Under existing technical conditions, after the development of voice interaction products is completed, performance testing is required to determine whether the performance of the developed voice interaction products meets the design requirements. The existing performance testing method generally involves manually asking simulated questions to the voice interaction products, which has problems such as low testing efficiency, inadequate testing, and high labor consumption. Summary of the Invention

[0003] In view of this, the present invention aims to overcome the defects in the prior art and proposes a voice interaction product testing method, device and product based on artificial intelligence.

[0004] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0005] In a first aspect, the present invention discloses a voice interaction product testing method based on artificial intelligence, comprising: generating corresponding questions based on a selected question type using a first artificial intelligence large model, wherein the question type is used to characterize the field to which the question belongs;

[0006] Convert the question into voice;

[0007] The voice interaction product to be tested responds to the question voice and outputs the corresponding answer voice;

[0008] Convert the answer voice into text answer;

[0009] The second artificial intelligence model is used to evaluate the accuracy of the matching between the text answer and the corresponding question, and the accuracy is output as the test result.

[0010] In another embodiment of the present invention, a second artificial intelligence large model is used to evaluate the accuracy of matching text answers with corresponding questions, and the accuracy is output as a test result, including: recording the number of questions belonging to the same question class, and the test result is the average value of the corresponding accuracy of all questions in the same question class.

[0011] In another embodiment of the present invention, the test result further includes the number of questions asked in the same question category.

[0012] In another embodiment of the present invention, a first threshold and a sequence of question types are set. If the average value is higher than the first threshold, the currently selected question type is replaced with the next question type, and the first artificial intelligence model is used to generate corresponding questions.

[0013] In another embodiment of the present invention, the method further includes: setting a second threshold and a sequence of question classes; if the running time of using the currently selected question class and the first artificial intelligence large model to generate corresponding question questions exceeds the second threshold, the currently selected question class is replaced with the next question class, and the first artificial intelligence large model is used again to generate corresponding question questions.

[0014] In another embodiment of the present invention, the method further includes: setting a third threshold and a sequence of question classes; if the number of questions recorded in the same question class is greater than the third threshold, the currently selected question class is replaced with the next question class, and the first artificial intelligence model is used to generate corresponding questions.

[0015] In another embodiment of the present invention, the test results are in a spreadsheet format document.

[0016] In a second aspect, the present invention discloses a voice interaction product testing device based on artificial intelligence, the device comprising:

[0017] A question generation module is used to generate corresponding questions based on the selected question type using the first artificial intelligence model, wherein the question type is used to characterize the field to which the question belongs;

[0018] The voice conversion module is used to convert the question into the voice of the question;

[0019] The test module is used for the voice interaction product to be tested to respond to the question voice and output the corresponding answer voice;

[0020] A text conversion module is used to convert the answer voice into text answers;

[0021] The evaluation result output module is used to use the second artificial intelligence model to evaluate the accuracy of the matching between the text answer and the corresponding question, and output the accuracy as the test result.

[0022] In a third aspect, the present invention discloses an electronic device comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0023] In a fourth aspect, a computer program product includes a computer program, which implements the above method when executed by a processor.

[0024] Compared with the prior art, the present invention has the following advantages:

[0025] The present invention discloses a method, device and product for testing a voice interaction product based on artificial intelligence, comprising: using a first artificial intelligence large model to generate corresponding questions according to a selected question type; converting the questions into question voices; the voice interaction product to be tested outputs corresponding answer voices in response to the question voices; converting the answer voices into text answers; using a second artificial intelligence large model to evaluate the accuracy of matching the text answers with the corresponding questions, and outputting the accuracy as a test result. The present invention discloses a method, device and product for testing a voice interaction product based on artificial intelligence, comprising: using a first artificial intelligence large model to generate questions; using a second artificial intelligence large model to evaluate the accuracy of matching the text answers with the corresponding questions, and outputting the test results, and having the characteristics of a high degree of automation in testing voice interaction products, sufficient testing and accurate test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0027] In the attached figure:

[0028] Figure 1 This is a schematic diagram of a voice interaction product testing method based on artificial intelligence according to an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the principles of a voice interaction product testing method based on artificial intelligence according to an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of a question sequence for a voice interaction product testing method based on artificial intelligence according to an embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of the average accuracy of a voice interaction product testing method based on artificial intelligence according to an embodiment of the present invention;

[0032] Figure 5 This is a schematic diagram of an artificial intelligence-based voice interaction product testing device according to an embodiment of the present invention;

[0033] Figure 6 This is a schematic diagram of an electronic device for testing voice interaction products based on artificial intelligence according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0035] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0036] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0037] In the description of the present invention, it should be further clarified that the terms "first," "second," etc. are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first," "second," etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0038] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0039] like Figure 1 and 2 As shown, the present invention discloses a voice interaction product testing method based on artificial intelligence, comprising:

[0040] Step S101: Generate corresponding questions based on the selected question type using the first artificial intelligence model, where the question type is used to characterize the field to which the question belongs;

[0041] In this embodiment, the first artificial intelligence big model can be an artificial intelligence big model such as deepseek. For example, the question class represents a question in a certain field, such as geography, history, cultural common sense, etc. In this embodiment, according to the application scenario of the voice interaction product to be tested, several relevant question classes are selected, and then the requirements for generating questions of a certain question class are input into the deepseek artificial intelligence big model. The deepseek artificial intelligence big model can generate several questions related to this category. For example: a question class of geography, a corresponding question is: Which island is the largest island in the world?

[0042] Step S102, converting the question into voice;

[0043] For example, the text-based questions output by the first artificial intelligence model are converted into voice form.

[0044] Step S103: The voice interaction product to be tested responds to the question voice and outputs a corresponding answer voice;

[0045] In this embodiment, the voice interaction product being tested may be a voice interaction product used in fields such as education, tourism, transportation, and entertainment, which can output corresponding voice answers to voice questions raised by users;

[0046] Step S104: convert the answer voice into a text answer;

[0047] In this embodiment, the answer voice output by the voice interaction product is converted into text form.

[0048] In step S105, the second artificial intelligence model is used to evaluate the accuracy of the matching between the text answer and the corresponding question, and the accuracy is output as the test result.

[0049] On the basis of the previous embodiment, in another embodiment of the present invention, as Figure 4 As shown, the second artificial intelligence model is used to evaluate the accuracy of matching text answers with corresponding questions, and the accuracy is output as the test result, including: recording the number of questions belonging to the same question class. The test result is the average value of the corresponding accuracy of all questions in the same question class.

[0050] In this embodiment, the test result also includes the number of questions asked in the same question category. By outputting the number of questions asked in a certain category, more detailed feedback on the test result can be achieved.

[0051] In this embodiment, according to the selected question type, the first artificial intelligence model continuously generates corresponding questions and converts them into question voices. Correspondingly, the voice interaction product to be tested outputs the corresponding answer voice, which is then converted into text form. For each question, the second artificial intelligence model evaluates the accuracy of the degree of matching between a question and the answer output by the voice interaction product. The accuracy of all questions of this question type is averaged to obtain the average accuracy corresponding to this question type.

[0052] In this embodiment, the second artificial intelligence model can be an artificial intelligence model such as DeepSeek. For example, the second artificial intelligence model is fed a question and a corresponding text answer, such as "Which island is the largest in the world?" Greenland. The second artificial intelligence model DeepSeek is then asked to evaluate the accuracy of the match between the question and the answer. The second artificial intelligence model DeepSeek returns an accuracy of 100%. Similarly, the second artificial intelligence model DeepSeek can return corresponding accuracy rates for all questions in this question type, and then the average accuracy rate of questions in this question type can be calculated.

[0053] On the basis of the previous embodiment, in another embodiment of the present invention, as Figure 3 As shown, a first threshold and a sequence of question types are set. If the average value is higher than the first threshold, the currently selected question type is replaced with the next question type, and the first artificial intelligence model is used to generate corresponding questions.

[0054] In this embodiment, if the average value is higher than the first threshold, it proves that the accuracy of the answers output by the tested voice interaction product for questions of this question type meets the design requirements, and then the questions of this question type can be tested at a later time to save test time and improve test efficiency, and the next question type can be tested to achieve the purpose of managing the test time of question types.

[0055] In this embodiment, the question class sequence is a pre-set sequence including several question classes based on the test requirements of the voice interaction product to be tested. The selected question classes are replaced one by one in the sequence order later.

[0056] In another embodiment of the present invention, the method further includes: setting a second threshold and a sequence of question classes; if the running time of using the currently selected question class and the first artificial intelligence large model to generate corresponding question questions exceeds the second threshold, the currently selected question class is replaced with the next question class, and the first artificial intelligence large model is used again to generate corresponding question questions.

[0057] In this embodiment, if a question is generated in a certain question type and the test time of the voice interaction product exceeds the set threshold, this question type will no longer be tested, the test results will be saved, and the test of the next question type will be started to improve the efficiency of the test.

[0058] In another embodiment of the present invention, the method further includes: setting a third threshold and a sequence of question classes; if the number of questions recorded in the same question class is greater than the third threshold, the currently selected question class is replaced with the next question class, and the first artificial intelligence model is used to generate corresponding questions.

[0059] In this embodiment, if the number of questions generated in a certain question type exceeds a set threshold, the question type will no longer be tested, the test results will be saved, and the test of the next question type will be started.

[0060] In this embodiment, the test result is a spreadsheet document.

[0061] like Figure 5 As shown, the present invention also discloses a voice interaction product testing device based on artificial intelligence, the device comprising:

[0062] The question generation module 501 is used to generate corresponding questions based on the selected question type using the first artificial intelligence model, wherein the question type is used to represent the field to which the question belongs;

[0063] The voice conversion module 502 is used to convert the question into a voice.

[0064] Testing module 503, configured for the voice interaction product to be tested to respond to the question voice and output the corresponding answer voice;

[0065] A text conversion module 504 is used to convert the answer voice into a text answer;

[0066] The evaluation result output module 505 is used to use the second artificial intelligence model to evaluate the accuracy of the matching between the text answer and the corresponding question, and output the accuracy as the test result.

[0067] The present invention also discloses an electronic device, such as Figure 6 As shown, an embodiment is disclosed, which is a block diagram of an electronic device suitable for testing the above-mentioned artificial intelligence-based voice interaction product.

[0068] The electronic device 60 of this embodiment includes a processor 601, which can perform various appropriate actions and processes according to the program stored in the ROM 602 or the program loaded from the storage part 608 into the RAM 603. The processor 601 may include, for example, a general-purpose microprocessor, an instruction set processor and / or a related chipset and / or a dedicated microprocessor, etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present invention.

[0069] RAM 603 stores various programs and data required for the operation of electronic device 60. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 executes the programs in ROM 602 and / or RAM 603 to perform various operations according to the method flow of the embodiment of the present invention. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603, and processor 601 may also execute the programs stored in one or more memories to perform various operations according to the method flow of the embodiment of the present invention.

[0070] According to an embodiment of the present invention, the electronic device 60 may further include an I / O interface 605, which is also connected to the bus 604. The electronic device 60 may further include one or more of the following components connected to the I / O interface 605: an input unit 606 including a keyboard, a mouse, etc.; an output unit 607 including a cathode ray tube, a liquid crystal display, and a speaker; a storage unit 608 including a hard disk; and a communication unit 609 including a network interface card such as a LAN card or a modem. The communication unit 609 performs communication processing via a network such as the Internet. A drive 6010 is also connected to the I / O interface 605 as needed. Removable media 6011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed in the drive 6010 as needed, so that computer programs read therefrom can be installed into the storage unit 608 as needed.

[0071] The present invention also provides a computer-readable storage medium.

[0072] The computer-readable storage medium may be included in the electronic device / device system described in the above embodiments, or may exist independently and not be incorporated into the electronic device / device. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of the present invention.

[0073] According to embodiments of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples include, but are not limited to, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0074] Embodiments of the present invention also include a computer program product.

[0075] The computer program product includes a computer program, which contains program code for executing the method provided by the embodiment of the present invention. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the method provided by the embodiment of the present invention.

[0076] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal over a network medium. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0077] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written by any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedural and / or object-oriented programming languages. Programming languages ​​include, but are not limited to, Java, C++, Python, C language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, 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 can be connected to the user computing device through any type of network, including a local area network or a wide area network, or can be connected to an external computing device.

[0078] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes may occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, as well as the combination of boxes in the block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or may be implemented using a combination of dedicated hardware and computer instructions. It will be understood by those skilled in the art that the features described in the various embodiments and / or claims of the present invention may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in the various embodiments and / or claims of the present invention may be combined and / or coupled in various ways, and all such combinations and / or couplings fall within the scope of the present invention.

[0079] The embodiments of the present invention have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. Although each embodiment has been described above separately, this does not mean that the measures in each embodiment cannot be advantageously used in combination. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A voice interaction product testing method based on artificial intelligence, characterized in that: include: Generate corresponding questions based on the selected question type using the first artificial intelligence model, wherein the question type is used to characterize the field to which the question belongs; Converting the question into voice; The voice interaction product to be tested responds to the question voice and outputs a corresponding answer voice; Convert the answer voice into a text answer; The second artificial intelligence model is used to evaluate the accuracy of the matching between the text answer and the corresponding question, and the accuracy is output as a test result.

2. The method for testing a voice interaction product based on artificial intelligence according to claim 1, characterized in that: The second artificial intelligence large model is used to evaluate the accuracy of the matching between the text answer and the corresponding question, and the accuracy is output as a test result, including: recording the number of questions belonging to the same question class, and the test result is the average value of the corresponding accuracy of all the questions in the same question class.

3. The method for testing a voice interaction product based on artificial intelligence according to claim 2, characterized in that: The test result also includes the number of the questions that belong to the same question category.

4. The method for testing a voice interaction product based on artificial intelligence according to claim 3, characterized in that: A first threshold and a sequence of the question classes are set. If the average value is higher than the first threshold, the currently selected question class is replaced with the next question class, and the first artificial intelligence model is used to generate the corresponding question.

5. The method for testing a voice interaction product based on artificial intelligence according to claim 3, characterized in that: The method also includes: setting a second threshold and a sequence of the question classes; if the running time of using the currently selected question class and the first artificial intelligence model to generate the corresponding question exceeds the second threshold, the currently selected question class is replaced with the next question class, and the first artificial intelligence model is used again to generate the corresponding question.

6. The method for testing a voice interaction product based on artificial intelligence according to claim 3, characterized in that: The method also includes: setting a third threshold and a sequence of the question classes; if the number of questions recorded in the same question class is greater than the third threshold, replacing the currently selected question class with the next question class, and then using the first artificial intelligence model to generate the corresponding questions.

7. The method for testing a voice interaction product based on artificial intelligence according to claim 1, characterized in that: The test results are in the form of a spreadsheet document.

8. An artificial intelligence-based voice interaction product testing device, characterized by: The device comprises: A question generation module is used to generate corresponding questions based on the selected question type using the first artificial intelligence model, wherein the question type is used to characterize the field to which the question belongs; A voice conversion module, used to convert the question into a voice; A testing module is used for the voice interaction product to be tested to respond to the question voice and output a corresponding answer voice; A text conversion module, used to convert the answer voice into a text answer; The evaluation result output module is used to use the second artificial intelligence model to evaluate the accuracy of the matching between the text answer and the corresponding question, and output the accuracy as the test result.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images