Product use scene determination method and device based on user comment analysis, electronic equipment, storage medium and computer program product

Abstract

The invention relates to a product use scene determination method and device based on user comment analysis, electronic equipment, a storage medium and a computer program product. The product use scene determination method based on user comment analysis comprises the steps of obtaining target comment data of a target product; inputting the target comment data and a pre-constructed cue word template into a large language model to obtain a scene recognition result for the target comment data; retrieving from a pre-constructed scene database based on the scene recognition result to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as a use scene of the target product, the scene database being pre-constructed based on comment data of a plurality of products of the to-be-analyzed category, and the comment data being the comment data of a plurality of products of the to-be-analyzed category; the to-be-analyzed category is the same as the category of the target product; the real use scene of the product can be determined through the comment data of the user, the design efficiency of the product can be further improved, and the use comfort of the product is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, electronic device, storage medium and computer program product for determining a product usage scenario based on user review analysis. Background Art

[0002] With the rapid development of the Internet, e-commerce, and social media, more and more products are sold through the Internet, and more and more users are accustomed to shopping online and evaluating the product usage process and experience, which also includes a description of the product usage scenarios.

[0003] Since there is a certain difference between the product manufacturers / marketers’ promotion of the product’s target application scenarios and the actual user scenarios, the manufacturers will not have enough understanding of the product’s positioning and target users, which will lead to a misalignment between the product design and the actual user needs, affecting the product’s use effect. Therefore, it is of great significance to discover the real application scenarios of the product through massive user reviews. Summary of the invention

[0004] The product usage scenario determination method, device, electronic device, storage medium and computer program product provided by the exemplary embodiments of the present disclosure based on user review analysis can at least solve the above technical problems and other technical problems not mentioned above.

[0005] According to one aspect of the present disclosure, a method for determining product usage scenarios based on user review analysis is provided, the method comprising: acquiring target review data of a target product; inputting the target review data and a pre-constructed prompt word template into a large language model to obtain a scene recognition result for the target review data; searching from a pre-constructed scene database based on the scene recognition result to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as the usage scenario of the target product, wherein the scene database is pre-constructed based on review data of multiple products in a category to be analyzed, and the category to be analyzed is the same as the category of the target product.

[0006] Optionally, the scenario database is constructed through the following operations: obtaining review data of multiple products in the category to be analyzed; extracting usage scenario names in the review data; mapping the usage scenario names to a vector space to obtain usage scenario vectors of the multiple products in the category to be analyzed, and using the usage scenario vectors of the multiple products in the category to be analyzed as the scenario database.

[0007] Optionally, extracting the usage scenario name from the review data includes: determining the usage scenario name according to the product scenario positioning of the category to be analyzed and the usage scenario involved in the review data.

[0008] Optionally, the method of retrieving from a pre-constructed scene database based on the scene recognition result to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as the usage scenario of the target product, includes: mapping the scene recognition result to a vector space to obtain a scene query vector; calculating the similarity value between the scene query vector and each of the usage scenario vectors in the scene database; and determining the scene corresponding to the usage scenario vector with the highest similarity value with the scene query vector among the usage scenario vectors as the usage scenario of the target product.

[0009] Optionally, the method of determining the scenario corresponding to the usage scenario vector having the highest similarity value with the scene query vector among the usage scenario vectors as the usage scenario of the target product includes: for the highest similarity value between each of the usage scenario vectors and the scene query vector, when the highest similarity value is greater than or equal to a preset threshold, determining the scenario corresponding to the usage scenario vector having the highest similarity value with the scene query vector among the usage scenario vectors as the usage scenario of the target product.

[0010] Optionally, the prompt word template includes task instructions, output format constraints and context examples. The task instructions are used to instruct the large language model to extract keywords or phrases describing the scene based on the target comment data to obtain the scene recognition result. The output format constraints are used to limit the form of the scene recognition result output by the large language model. The context examples are used to show the large language model the embodiment of the task instructions and the output format constraints in actual applications.

[0011] According to another aspect of the present disclosure, there is also provided a device for determining a product usage scenario based on user review analysis, the device for determining a product usage scenario based on user review analysis comprising:

[0012] The data acquisition unit is configured to: acquire target review data of a target product;

[0013] A scene recognition unit is configured to: input the target comment data and a pre-built prompt word template into a large language model to obtain a scene recognition result for the target comment data;

[0014] The scene determination unit is configured to: search from a pre-constructed scene database based on the scene recognition result to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as the usage scene of the target product, wherein the scene database is pre-constructed based on review data of multiple products in a category to be analyzed, and the category to be analyzed is the same as the category of the target product.

[0015] According to another aspect of an embodiment of the present disclosure, an electronic device is also provided, comprising: at least one processor; and at least one memory storing computer executable instructions, wherein when the computer executable instructions are executed by the at least one processor, the at least one processor is prompted to execute any of the above-described methods for determining product usage scenarios based on user review analysis.

[0016] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium storing instructions is also provided. When the instructions are executed by at least one processor, the at least one processor is prompted to execute any of the above-described methods for determining product usage scenarios based on user review analysis.

[0017] According to another aspect of an embodiment of the present disclosure, a system is also provided, comprising at least one computing device and at least one storage device storing instructions, wherein when the instructions are executed by the at least one computing device, the at least one computing device is prompted to execute any of the above-described methods for determining product usage scenarios based on user review analysis.

[0018] According to another aspect of an embodiment of the present disclosure, a computer program product is also provided, including a computer program / instruction, which, when executed by a processor, implements the method for determining a product usage scenario based on user review analysis as described in any one of the above.

[0019] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0020] The method, device, electronic device, storage medium and computer program product for determining product usage scenarios based on user review analysis disclosed in the present invention can determine the actual usage scenarios of a product through user review data, and can further improve the design efficiency of the product and enhance the comfort of product use. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0022] Figure 1A schematic diagram showing a method for determining a product usage scenario based on user review analysis in an exemplary embodiment of the present disclosure;

[0023] Figure 2 A block diagram showing a device for determining a product usage scenario based on user review analysis in an exemplary embodiment of the present disclosure is shown;

[0024] Figure 3 A block diagram illustrating an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation methods described in the following examples do not represent all implementation methods consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the attached claims.

[0027] It should be noted that the phrase "at least one of the items" in the present disclosure includes three types of parallel situations: "any one of the items", "a combination of any number of the items", and "all of the items". For example, "including at least one of A and B" includes the following three parallel situations: (1) including A; (2) including B; (3) including A and B. Another example is "executing at least one of step 1 and step 2" which means the following three parallel situations: (1) executing step 1; (2) executing step 2; (3) executing step 1 and step 2.

[0028] With the booming development of the Internet, e-commerce and social media, online shopping has become the mainstream consumption model. Consumers not only buy goods, but also like to share their experience, including vivid descriptions of product usage scenarios. These user-generated contents provide valuable feedback to the market.

[0029] However, when promoting products, product manufacturers or marketers often describe product application scenarios based on idealized settings, which are often inconsistent with the actual usage scenarios of users in real life. This information asymmetry not only makes it difficult for manufacturers to accurately grasp the real needs of the target user group, but may also cause product design to deviate from user expectations, affecting the practicality and satisfaction of the product.

[0030] Therefore, in-depth exploration and analysis of user comments and accurate grasp of the product's real application scenarios are crucial to optimizing product design and improving user experience. It is an effective bridge connecting production and consumption and achieving accurate market positioning.

[0031] In order to solve the above problems, the present disclosure provides a method, device, electronic device, storage medium and computer program product for determining product usage scenarios based on user review analysis, which can determine the actual usage scenarios of products through user review data, and can further improve the design efficiency of products and improve the comfort of product use.

[0032] Next, we will refer to Figures 1 to 3 The present invention specifically describes the method, device, electronic device, storage medium and computer program product for determining product usage scenarios based on user review analysis.

[0033] Figure 1 A schematic diagram showing a method for determining a product usage scenario based on user review analysis in an exemplary embodiment of the present disclosure.

[0034] Reference Figure 1 , in step 101, target review data of a target product is obtained.

[0035] According to an exemplary embodiment of the present disclosure, the target review data is used to determine a usage scenario of a target product.

[0036] In step 102, the target comment data and the pre-built prompt word template are input into the large language model to obtain a scene recognition result for the target comment data.

[0037] According to an exemplary embodiment of the present disclosure, a prompt word template may include but is not limited to task instructions, output format constraints and context examples. Task instructions may be used to instruct the large language model to extract keywords or phrases describing the scene based on the target comment data to obtain a scene recognition result. The output format constraints may be used to limit the form of the scene recognition result output by the large language model. The context examples may be used to demonstrate to the large language model the embodiment of task instructions and output format constraints in actual applications.

[0038] The prompt word template can guide the large language model to identify product application scenarios based on an input user comment (for example, target comment data), and output the analysis result in a structured form, namely, the scenario recognition result; this process will be described in detail below.

[0039] According to an exemplary embodiment of the present disclosure, the structure of the prompt word template may be as follows:

[0040] Task instructions: Please extract keywords or phrases describing the scene based on the comments. If there is no relevant description, please output "none".

[0041] Output format constraints: The output results must comply with the following output format: Scenario: [relevant description or "None"].

[0042] Context example: Here is an example: "User comment input": The overall appearance is beautiful, grand, and does not take up space! It is suitable for tenants, and I like it. It is inexpensive and good quality, and it is quite easy to use. It is good in the living room. The overall effect is good. The installation is professional and fast. The installer is meticulous and awesome. "Analysis result output": Scenario: Place it in the living room.

[0043] Task instructions: Now please refer to the above example to analyze the following user comment input data (i.e. target comment data) and extract keywords or phrases describing the scene from the comments. If there is no relevant description, please output "none".

[0044] "User Comment Input": This Bluetooth headset is a great commuter tool! When you are on the subway every day, you can put it on to block out the noise and immerse yourself in the world of music. The sound quality is clear and comfortable to wear, and your ears will not get tired even after long-term use. Moreover, it also supports touch operation, which is super convenient for answering calls and switching songs, making the commute to work easy and enjoyable!

[0045] As an example only, the above-mentioned prompt word template and the above-mentioned user comment input (i.e., target comment data) can be input into the large language model together, that is, the above-mentioned prompt word template and the above-mentioned user comment input (i.e., target comment data) can be spliced ​​and input into the large language model; the above-mentioned prompt word template can guide the large language model to perform tasks related to scene extraction through the task instructions therein, and limit the form of the output data of the large language model through output format constraints, that is, use relevant descriptions of the scene or "none", and guide the large language model through context examples to extract scenes according to a certain user comment input and output actual application examples to perform related tasks of scene extraction for other user comment inputs in the task instructions.

[0046] As an example only, if the target comment data is the above user comment input, the large language model can obtain the following scene recognition results based on the prompt word template: Scene: subway.

[0047] According to an exemplary embodiment of the present disclosure, the large language model may include but is not limited to a GPT (Generative Pre-trained Transformer) series model and the like.

[0048] In step 103, based on the scene recognition result, a search is performed from a pre-constructed scene database to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as the usage scene of the target product, wherein the scene database is pre-constructed based on the review data of multiple products in the category to be analyzed, and the category to be analyzed is the same as the category of the target product.

[0049] According to an exemplary embodiment of the present disclosure, the scene database is constructed through the following operations 103-1 to 103-3:

[0050] In operation 103 - 1 , review data of a plurality of products in the category to be analyzed may be obtained.

[0051] First, relevant network data sources of a certain type of product to be analyzed may be determined. These data sources may include but are not limited to online e-commerce, social media platforms, product forums, etc.

[0052] The relevant data of the target network data source can be crawled through a network collection method. Specifically, the network collection method may include but is not limited to using a network crawler technology, an API (Application Programming Interface) call or a data exchange protocol.

[0053] As an example only, you can choose a web crawler method to automatically collect review data of multiple products in the category to be analyzed based on preset crawling rules and keywords.

[0054] Next, based on the review data of multiple products in this category, professionals can build a product scenario library for this category.

[0055] In operation 103 - 2 , the usage scenario name in the comment data is extracted.

[0056] As an example only, the usage scenario name can be determined based on the product scenario positioning of the category to be analyzed and the usage scenario involved in the review data.

[0057] This process can rely on professional product designers to define the names of various usage scenarios, including the corresponding usage scenarios that the product design originally positioned, as well as the usage scenarios analyzed and summarized by professionals by reviewing a certain amount of review data. These usage scenario names can be summarized into a product scenario library.

[0058] Just as an example, when the target product is "noise-cancelling headphones", the product scenario library may include but is not limited to the following scenario names: outdoor, bus, rail transit, air transportation, cafe, park.

[0059] In operation 103 - 3 , the usage scenario names are mapped to the vector space to obtain usage scenario vectors of multiple products in the category to be analyzed, so as to use the usage scenario vectors of multiple products in the category to be analyzed as a scenario database.

[0060] Each usage scenario name in the product scenario library can be converted into a vector space by using text vector embedding methods including but not limited to Word2Vec, Bert, etc., to construct a corresponding scenario vector library.

[0061] According to an exemplary embodiment of the present disclosure, when searching in a scene database (product scene library or scene vector library) based on scene recognition results, it can be achieved by using wildcards and the like to perform fuzzy search in the product scene library based on the scene recognition results, or it can be achieved by mapping the scene recognition results to a vector space and then searching in the scene vector library by similarity values. Searching by vector mapping can achieve higher search accuracy through semantic understanding.

[0062] Next, the specific implementation method of retrieval through vector mapping is introduced.

[0063] According to an exemplary embodiment of the present disclosure, the scene recognition result can be mapped to a vector space to obtain a scene query vector; the similarity value between the scene query vector and each usage scenario vector in the scene database is calculated; and the scene corresponding to the usage scenario vector having the highest similarity value with the scene query vector among each usage scenario vector is determined as the usage scenario of the target product.

[0064] The scene recognition result name output by the large language model can be converted into a vector space using text vector embedding methods including but not limited to Word2Vec and Bert to obtain a scene query vector.

[0065] The similarity between the scene query vector and each vector in the scene vector library can be calculated in turn, and the scene vector with the highest similarity to the query vector can be found.

[0066] The similarity value between the scene query vector and each used scene vector in the scene database may be calculated using methods including but not limited to cosine similarity.

[0067] According to an exemplary embodiment of the present disclosure, for the highest similarity value between each usage scenario vector and the scene query vector, when the highest similarity value is greater than or equal to a preset threshold, the scene corresponding to the usage scenario vector with the highest similarity value with the scene query vector among the usage scenario vectors can be determined as the usage scenario of the target product.

[0068] Different preset thresholds may be set according to different application fields. As an example only, the specific value of the preset threshold may be 0.7.

[0069] If the highest similarity value is greater than the preset threshold, it can be regarded as that the target product usage scenario based on the target comment data is successfully identified, and the scene name corresponding to the usage scenario vector with the highest similarity value with the scene query vector can be used as the final result of the target product usage scenario extracted from the target comment data.

[0070] Just as an example, if the scene query vector corresponding to the scene recognition result "subway" of the above target comment data is searched in the product scene library of the above target product "noise cancelling headphones", it may be calculated that the similarity value between it and the usage scene vector of "rail transit" is the highest, which is 0.85. Then, it can be determined that "rail transit" is the usage scene of the target product "noise cancelling headphones".

[0071] When the highest similarity value is less than a preset threshold, it can be considered that the usage scenario of the target product cannot be determined based on the target review data.

[0072] Figure 2 A block diagram of a device for determining a product usage scenario based on user review analysis in an exemplary embodiment of the present disclosure is shown.

[0073] Reference Figure 2 The exemplary embodiment of the present disclosure further provides a device 200 for determining a product usage scenario based on user review analysis, which may include but is not limited to a data acquisition unit 201 , a scenario recognition unit 202 , and a scenario determination unit 203 .

[0074] The data acquisition unit 201 may acquire target review data of a target product.

[0075] The scene recognition unit 202 may input the target comment data and the pre-built prompt word template into the large language model to obtain a scene recognition result for the target comment data.

[0076] The scene determination unit 203 can search from a pre-constructed scene database based on the scene recognition result to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as the usage scene of the target product, wherein the scene database is pre-constructed based on the review data of multiple products in the category to be analyzed, and the category to be analyzed is the same as the category of the target product.

[0077] It is understandable that in the exemplary embodiment of the above-mentioned device 200 for determining product usage scenarios based on user review analysis, the specific implementation process is roughly the same as the exemplary embodiment of the above-mentioned method for determining product usage scenarios based on user review analysis, and will not be repeated here. The device 200 for determining product usage scenarios based on user review analysis can be configured as software, hardware, firmware, or any combination of the above items to perform specific functions. For example, these devices may correspond to dedicated integrated circuits, pure software codes, or modules that combine software and hardware. In addition, one or more functions implemented by these devices may also be uniformly executed by components in physical entity devices (for example, processors, clients, or servers, etc.).

[0078] Figure 3 A block diagram illustrating an electronic device according to an exemplary embodiment of the present disclosure.

[0079] Reference Figure 3 The electronic device 300 includes at least one memory 301 and at least one processor 302, wherein the at least one memory 301 stores a set of computer executable instructions. When the computer executable instruction set is executed by the at least one processor 302, a method for determining a product usage scenario based on user review analysis according to an exemplary embodiment of the present disclosure is executed.

[0080] As an example, the electronic device 300 may be a PC, a tablet device, a personal digital assistant, a smart phone, or other device capable of executing the above-mentioned instruction set. Here, the electronic device 300 is not necessarily a single electronic device, but may also be any device or circuit capable of executing the above-mentioned instruction (or instruction set) individually or in combination. The electronic device 300 may also be part of an integrated control system or a system manager, or may be configured as a portable electronic device interconnected with a local or remote (e.g., via wireless transmission) interface.

[0081] In the electronic device 300, the processor 302 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller or a microprocessor. As an example and not limitation, the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0082] The processor 302 may execute instructions or codes stored in the memory 301, wherein the memory 301 may also store data. Instructions and data may also be sent and received over a network via a network interface device, wherein the network interface device may employ any known transmission protocol.

[0083] The memory 301 may be integrated with the processor 302, for example, by placing RAM or flash memory within an integrated circuit microprocessor or the like. In addition, the memory 301 may include a separate device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system. The memory 301 and the processor 302 may be operatively coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the processor 302 can read files stored in the memory.

[0084] In addition, the electronic device 300 may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the electronic device 300 may be connected to each other via a bus and / or a network.

[0085] According to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing instructions may also be provided, wherein when the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the above-mentioned product usage scenario determination method based on user review analysis.

[0086] Examples of computer-readable storage media include read-only memory (ROM), random-access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), flash memory, nonvolatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disk storage, hard disk drive (HDD), solid state drive (SSD), card storage (such as, multimedia card, secure digital (SD) card or extreme digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other device, any other device is configured to store computer programs and any associated data, data files and data structures in a non-transitory manner and provide the computer programs and any associated data, data files and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the above-mentioned computer-readable storage medium can be run in an environment deployed in a computer device such as a client, a host, an agent device, a server, etc. In addition, in one example, the computer program and any associated data, data files and data structures are distributed on a networked computer system, so that the computer program and any associated data, data files and data structures are stored, accessed and executed in a distributed manner by one or more processors or computers. It should be noted that the instructions can also be used to execute additional steps in addition to the above steps or to perform more specific processing when executing the above steps. These additional steps and further processing contents have been mentioned in the description of the relevant methods, so they will not be repeated here to avoid repetition.

[0087] Another embodiment of the present disclosure relates to a system including at least one computing device and at least one storage device storing instructions, wherein the instructions, when executed by the at least one computing device, prompt the at least one computing device to execute the above-mentioned method for determining product usage scenarios based on user review analysis.

[0088] It should be noted that the system according to the exemplary embodiments of the present disclosure can completely rely on the execution of computer programs or instructions to realize corresponding functions, that is, each unit corresponds to each step in the functional architecture of the computer program, so that the entire system is called through a special software package (e.g., lib library) to realize the corresponding functions.

[0089] On the other hand, when the above-mentioned system is implemented in software, firmware, middleware or microcode, the program code or code segment for performing the corresponding operation can be stored in a computer-readable medium such as a storage medium, so that at least one processor or at least one computing device can perform the corresponding operation by reading and running the corresponding program code or code segment.

[0090] According to an exemplary embodiment of the present disclosure, the storage device may be integrated with the computing device, for example, RAM or flash memory is arranged within an integrated circuit microprocessor, etc. In addition, the storage device may include an independent device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system. The storage device and the computing device may be operationally coupled, or may communicate with each other, such as through an I / O port, a network connection, etc., so that the computing device can read instructions stored in the storage device.

[0091] Another embodiment of the present disclosure relates to a computer program product, including a computer program / instruction, which, when executed by a processor, implements the method for determining a product usage scenario based on user review analysis as described in any one of the above.

[0092] According to the method, device, electronic device, storage medium and computer program product for determining product usage scenarios based on user review analysis provided in the present disclosure, it is possible to determine the actual usage scenarios of a product through user review data, and further improve the design efficiency of the product and enhance the comfort of product use.

[0093] The above describes various exemplary embodiments of the present disclosure, and it should be understood that the above description is only exemplary and not exhaustive, and the present disclosure is not limited to the disclosed exemplary embodiments. Without departing from the scope and spirit of the present disclosure, many modifications and changes are obvious to those of ordinary skill in the art. Therefore, the scope of protection of the present disclosure should be based on the scope of the claims.

Claims

1. A method for determining product usage scenarios based on user review analysis, characterized in that: The method for determining product usage scenarios based on user review analysis includes: Get target review data for target products; Inputting the target comment data and a pre-built prompt word template into a large language model to obtain a scene recognition result for the target comment data; Based on the scene recognition result, a search is performed from a pre-constructed scene database to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as the usage scene of the target product, wherein the scene database is pre-constructed based on review data of multiple products in a category to be analyzed, and the category to be analyzed is the same as the category of the target product.

2. The method for determining product usage scenarios based on user review analysis according to claim 1, characterized in that: The scene database is constructed by the following operations: Obtaining review data of multiple products in the category to be analyzed; Extracting the usage scenario name from the comment data; The usage scenario names are mapped to a vector space to obtain usage scenario vectors of the multiple products in the category to be analyzed, so as to use the usage scenario vectors of the multiple products in the category to be analyzed as the scenario database.

3. The method for determining product usage scenarios based on user review analysis according to claim 2, characterized in that: The extracting the usage scenario name from the comment data includes: The usage scenario name is determined according to the product scenario positioning of the category to be analyzed and the usage scenario involved in the review data.

4. The method for determining product usage scenarios based on user review analysis according to claim 2, characterized in that: The searching from a pre-built scene database based on the scene recognition result to obtain a target scene with the highest similarity value to the scene recognition result, so as to determine the target scene as the usage scene of the target product, includes: Mapping the scene recognition result to a vector space to obtain a scene query vector; Calculating a similarity value between the scene query vector and each of the usage scene vectors in the scene database; The scenario corresponding to the usage scenario vector having the highest similarity value with the scenario query vector among the usage scenario vectors is determined as the usage scenario of the target product.

5. The method for determining product usage scenarios based on user review analysis according to claim 4, characterized in that: The step of determining, among the usage scenario vectors, a scenario corresponding to a usage scenario vector having the highest similarity value with the scenario query vector as a usage scenario of the target product includes: For the highest similarity value between each of the usage scenario vectors and the scenario query vector, When the highest similarity value is greater than or equal to a preset threshold, the scenario corresponding to the usage scenario vector having the highest similarity value with the scenario query vector among the usage scenario vectors is determined as the usage scenario of the target product.

6. The method for determining product usage scenarios based on user review analysis according to any one of claims 1 to 5, characterized in that: The prompt word template includes task instructions, output format constraints and context examples. The task instructions are used to instruct the large language model to extract keywords or phrases describing the scene based on the target comment data to obtain the scene recognition result. The output format constraints are used to limit the form of the scene recognition result output by the large language model. The context examples are used to show the large language model the embodiment of the task instructions and the output format constraints in actual applications.

7. A device for determining product usage scenarios based on user review analysis, characterized in that: The device for determining product usage scenarios based on user review analysis comprises: The data acquisition unit is configured to: acquire target review data of a target product; A scene recognition unit is configured to: input the target comment data and a pre-built prompt word template into a large language model to obtain a scene recognition result for the target comment data; The scene determination unit is configured to: search from a pre-constructed scene database based on the scene recognition result to obtain a target scene with the highest similarity value with the scene recognition result, so as to determine the target scene as the usage scene of the target product, wherein the scene database is pre-constructed based on review data of multiple products in a category to be analyzed, and the category to be analyzed is the same as the category of the target product.

8. An electronic device, characterized in that: include: at least one processor; at least one memory storing computer executable instructions, When the computer executable instructions are executed by the at least one processor, the at least one processor is prompted to execute the product usage scenario determination method based on user review analysis as described in any one of claims 1-6.

9. A computer-readable storage medium storing instructions, characterized in that: When the instructions are executed by at least one processor, the at least one processor is prompted to execute the product usage scenario determination method based on user review analysis as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method for determining a product usage scenario based on user review analysis as described in any one of claims 1 to 6 is implemented.

Images