Vehicle information processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a vehicle information processing method and device, equipment and a storage medium, and the method comprises the steps: responding to a vehicle condition configuration operation triggered by a user for a target vehicle, and obtaining the vehicle information of the target vehicle uploaded by the user; using a target cue word template corresponding to the vehicle condition configuration operation, combining the vehicle information to form a target cue word, and inputting the target cue word into a large language model, so that the large language model generates a target vehicle condition description according with a preset vehicle condition description rule according to the target cue word; determining video templates respectively corresponding to a plurality of vehicle appearance images uploaded by the user, and generating respective explanation documents of the plurality of vehicle appearance images according to the vehicle information and the target vehicle condition description; and generating an explanation video corresponding to the target vehicle according to the plurality of vehicle appearance images, the video template and the explanation copywriting. According to the scheme, the target vehicle condition description is generated through the large language model and is converted into the explanation video with the uniform format, and the user experience when the user releases or obtains the vehicle information is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a vehicle information processing method, device, equipment and storage medium. Background Art

[0002] In the used car trading scenario, sellers publish vehicle information of vehicles for sale through the used car trading platform, such as: vehicle brand, model, color, price, vehicle condition description (such as: vehicle newness, etc.). Buyers view the vehicle information of vehicles for sale published by sellers through the used car trading platform and select vehicles to trade with sellers.

[0003] In actual applications, when sellers publish vehicle information for sale on used car trading platforms, there is a tendency for the vehicle condition description to be irregular, such as including sensitive words prohibited by the platform, which will result in multiple failures in the release of vehicle information and affect the seller's user experience. In addition, the vehicle information for sale uploaded by different sellers to used car trading platforms is often expressed in a variety of ways, and buyers are inefficient in obtaining effective information from vehicle information in a variety of different ways of expression, and the experience is poor. Summary of the invention

[0004] Embodiments of the present invention provide a vehicle information processing method, apparatus, device and storage medium to enhance the user experience when publishing or obtaining vehicle information.

[0005] In a first aspect, an embodiment of the present invention provides a vehicle information processing method, the method comprising:

[0006] In response to a vehicle condition configuration operation triggered by a user for a target vehicle, obtaining vehicle information of the target vehicle uploaded by the user;

[0007] Using the target prompt word template corresponding to the vehicle condition configuration operation, combined with the vehicle information, to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with a preset vehicle condition description rule;

[0008] Determine the video templates corresponding to the multiple vehicle appearance images uploaded by the user;

[0009] generating explanation texts for each of the plurality of vehicle appearance images according to the vehicle information and the target vehicle condition description;

[0010] An explanation video corresponding to the target vehicle is generated according to the multiple vehicle appearance images, the video template and the explanation text.

[0011] In a second aspect, an embodiment of the present invention provides a vehicle information processing device, the device comprising:

[0012] An acquisition module, configured to acquire vehicle information of a target vehicle uploaded by a user in response to a vehicle condition configuration operation triggered by a user for the target vehicle;

[0013] A first processing module is used to use the target prompt word template corresponding to the vehicle condition configuration operation, combined with the vehicle information, to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with a preset vehicle condition description rule;

[0014] The second processing module is used to determine the video templates corresponding to the multiple vehicle appearance images uploaded by the user; generate explanation texts for the multiple vehicle appearance images according to the vehicle information and the target vehicle condition description; and generate an explanation video corresponding to the target vehicle according to the multiple vehicle appearance images, the video templates and the explanation texts.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor can at least implement the vehicle information processing method described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present invention provides a non-temporary machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor can at least implement the vehicle information processing method described in the first aspect.

[0017] In a fifth aspect, an embodiment of the present invention provides a computer program product, comprising: a computer program, when the computer program is executed by a processor of an electronic device, the processor can at least implement the vehicle information processing method as described in the first aspect.

[0018] In the solution provided by the embodiment of the present invention, first, in response to a vehicle condition configuration operation triggered by a user for a target vehicle, vehicle information of the target vehicle uploaded by the user is obtained, wherein the vehicle information is information edited by the user and may contain illegal content; then, a target prompt word template corresponding to the vehicle condition configuration operation is used in combination with the vehicle information to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with a preset vehicle condition description rule, and the content contained therein is all compliant; then, the video templates corresponding to the multiple vehicle appearance images uploaded by the user are determined, and the explanation texts of the multiple vehicle appearance images are generated according to the vehicle information and the target vehicle condition description; finally, an explanation video corresponding to the target vehicle is generated according to the multiple vehicle appearance images, the video template and the explanation text.

[0019] In this solution, the target prompt word template corresponding to the vehicle condition configuration operation and the vehicle information uploaded by the user are combined into a target prompt word and input into the large language model, so that the large language model generates a target vehicle condition description that conforms to the preset vehicle condition description rules. Using the target vehicle condition description as the vehicle condition description for uploading to the used car trading platform can effectively avoid the failure of vehicle information release due to non-compliant vehicle condition descriptions, thereby effectively improving the efficiency of vehicle information release. In addition, converting vehicle information, target vehicle condition descriptions, and vehicle appearance pictures into explanation videos with a unified format through video templates can improve the user's information acquisition efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A flow chart of a vehicle information processing method provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a vehicle condition configuration interface provided by an embodiment of the present invention;

[0023] Figure 3 A flowchart of a vehicle condition description generation method provided by an embodiment of the present invention;

[0024] Figure 4 A flowchart of another vehicle condition description generating method provided by an embodiment of the present invention;

[0025] Figure 5 A flowchart of another vehicle condition description generating method provided by an embodiment of the present invention;

[0026] Figure 6 A schematic diagram of the structure of a vehicle information processing device provided by an embodiment of the present invention;

[0027] Figure 7 For Figure 6 A schematic diagram of the structure of an electronic device corresponding to the vehicle information processing device provided in the illustrated embodiment. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0030] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the case where there is no conflict between the embodiments, the following embodiments and the features in the embodiments can be combined with each other. In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0031] In the used car trading scenario, sellers publish vehicle information of vehicles for sale (hereinafter referred to as target vehicles) through used car trading platforms. Among them, vehicle information can be roughly summarized into two types: one is the objective vehicle configuration parameters that are irrelevant to the user, including but not limited to the vehicle's brand, model, color, vehicle identification number, etc.; the other is the user's personal description of the vehicle's usage status, referred to as vehicle condition description, including but not limited to vehicle appearance description, vehicle mechanical condition description, vehicle accident record description, vehicle maintenance record description, etc.

[0032] In the traditional solution, the seller fills in the vehicle condition description by himself and uploads it to the used car trading platform. The used car platform will judge whether the vehicle condition description filled in by the seller complies with the rules according to the preset vehicle condition description rules, such as: judging whether the vehicle condition description contains sensitive words, and information suggesting that the buyer will leave the platform and conduct private transactions. When the vehicle condition description uploaded by the seller does not comply with the rules, the seller is prompted to re-upload the vehicle condition description, otherwise the sales information of the target vehicle will not be published on the used car trading platform. In view of this, when the seller publishes the vehicle information, the vehicle information may fail to be published multiple times due to the irregular vehicle condition description, affecting the user experience of the seller when publishing the vehicle information of the target vehicle.

[0033] After the seller publishes the vehicle information of the target vehicle on the used car trading platform, the buyer views the vehicle information of the vehicles for sale published by the seller through the used car trading platform and selects the vehicle to trade with the seller. In actual applications, the vehicle information of the vehicles for sale uploaded by different sellers to the used car trading platform is often expressed in various ways. For example, some sellers use a picture and text post in one typesetting format, while some sellers use a picture and text post in another typesetting format. When buyers obtain effective information from vehicle information in multiple different expression methods, there are problems of low efficiency and poor experience.

[0034] In addition, from the perspective of the used car trading platform, regular expressions are usually used to represent the vehicle condition description rules. Once loopholes are found in the vehicle condition description rules, the vehicle condition description rules need to be revised again, and developers need to rewrite the code, which consumes a lot of manpower and is inefficient.

[0035] In response to at least one of the above technical problems, an embodiment of the present invention provides a vehicle information processing method. In a scenario where a user publishes vehicle information of a target vehicle through a used car trading platform, first, in response to a vehicle condition configuration operation triggered by the user for the target vehicle, the vehicle information of the target vehicle uploaded by the user is obtained; then, the target prompt word template corresponding to the vehicle condition configuration operation is used, combined with the vehicle information, to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with the preset vehicle condition description rules. By generating a target vehicle condition description that complies with the preset vehicle condition description rules through a large language model, and using the target vehicle condition description as the vehicle condition description for uploading to a used car trading platform, the failure of vehicle information publishing due to non-compliant vehicle condition description can be effectively avoided, thereby effectively improving the efficiency of vehicle information publishing. Furthermore, it is also possible to determine the video templates corresponding to the multiple vehicle appearance images of the target vehicle uploaded by the user, and generate explanation texts for the multiple vehicle appearance images based on the vehicle information and the target vehicle condition description. Finally, based on the multiple vehicle appearance images, the video template and the explanation text, the explanation video corresponding to the target vehicle is generated, and converted into an explanation video with a unified format through the video template, which can improve the user's information acquisition efficiency.

[0036] In the following, some embodiments of the present invention are described in detail in conjunction with specific embodiments. In the case where there is no conflict between the embodiments, the following embodiments and features in the embodiments can be combined with each other.

[0037] The vehicle information processing method provided in the embodiment of the present invention can be executed by an electronic device, which can be a terminal device such as a PC, a laptop, a smart phone, etc., or a server. The server can be a physical server including an independent host, or a virtual server, or a cloud server or a server cluster.

[0038] Figure 1 A flow chart of a vehicle information processing method provided by an embodiment of the present invention, such as Figure 1 As shown, the following steps may be included:

[0039] 101. In response to a vehicle condition configuration operation triggered by a user for a target vehicle, obtain vehicle information of the target vehicle uploaded by the user.

[0040] 102. Use the target prompt word template corresponding to the vehicle condition configuration operation, combined with the vehicle information, to form a target prompt word and input it into the large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with the preset vehicle condition description rules.

[0041] 103. Determine video templates corresponding to the multiple vehicle appearance images of the target vehicle uploaded by the user.

[0042] 104. Generate explanation texts for multiple vehicle appearance images according to vehicle information and target vehicle condition description.

[0043] 105. Generate an explanation video corresponding to the target vehicle based on multiple vehicle appearance images, video templates and explanation texts.

[0044] In this embodiment, a user interface (UI) is provided for users to configure vehicle conditions, also known as a vehicle condition configuration interface. Users can fill in the vehicle condition description by themselves through the vehicle condition matching interface, that is, input the original vehicle condition description, and can also trigger the corresponding vehicle condition configuration operation through the vehicle condition configuration interface. For the vehicle condition configuration operation triggered by the user, a target vehicle condition description that meets the preset vehicle condition description rules is generated through a preset large language model (LLM).

[0045] Among them, the preset vehicle condition description rules include at least one compliance judgment rule, such as: the vehicle condition description must not contain a valid contact number, the vehicle condition description must not be less than 100 words, etc. In actual applications, the vehicle condition description rules can be customized.

[0046] Optionally, the vehicle condition configuration operation includes but is not limited to: a vehicle condition description generation operation, a vehicle condition description optimization operation, and a vehicle condition description correction operation. Among them, the vehicle condition description generation operation is used to automatically generate a target vehicle condition description that meets the preset vehicle condition description rules for the user based on the vehicle configuration parameters. In this scenario, the user can choose to input or not input the original vehicle condition description; the vehicle condition description optimization operation is used to optimize the original vehicle condition description input by the user to generate a target vehicle condition description that meets the preset vehicle condition description rules; the vehicle condition description correction operation is used to screen the illegal content in the original vehicle condition description input by the user that does not meet the preset vehicle condition description rules, so that the user can correct the original vehicle condition description so that the original vehicle condition description meets the preset vehicle condition description rules after correction.

[0047] Figure 2 A schematic diagram of a vehicle condition configuration interface provided by an embodiment of the present invention, such as Figure 2 As shown, the vehicle condition configuration interface includes an input box for users to input the original vehicle condition description, as well as "Generate", "Optimize", and "Correct" control keys. During the application process, the user can trigger the vehicle condition description generation operation by clicking the "Generate" control key, trigger the vehicle condition description optimization operation by clicking the "Optimize" control key, and trigger the vehicle condition description correction operation by clicking the "Correct".

[0048] It should be noted that Figure 2The vehicle condition configuration interface provided is for illustrative purposes only. In this embodiment, there are no limitations on the control key types, control key layout, and triggering method of the vehicle condition configuration operation contained in the vehicle condition configuration interface. For example, the vehicle condition description correction operation can be triggered in response to the user actively uploading the original vehicle condition description to the used car trading platform.

[0049] In the process of generating a target vehicle condition description that conforms to preset vehicle condition description rules through a preset large language model, specifically, in response to a vehicle condition configuration operation triggered by a user for a target vehicle, firstly obtain the vehicle information of the target vehicle uploaded by the user; then, combine the target prompt word template corresponding to the vehicle condition configuration operation pre-configured in the large language model to generate the target prompt word for input into the large language model; finally, the large language model generates the target vehicle condition description that conforms to the preset vehicle condition description rules corresponding to the target vehicle according to the target prompt word.

[0050] Optionally, the vehicle information of the target vehicle includes: vehicle configuration parameters of the target vehicle, and / or the original vehicle condition description input by the user. Based on the above description of the goal to be achieved by the vehicle condition configuration operation, in actual applications, in response to different vehicle condition configuration operations, corresponding vehicle information is obtained accordingly, for example, only vehicle configuration parameters or the original vehicle condition description can be obtained, or both vehicle configuration parameters and the original vehicle condition description can be obtained.

[0051] Optionally, the target prompt word template includes a preset vehicle condition description rule and a task description corresponding to the vehicle condition configuration operation. In this solution, by configuring the preset vehicle condition description rule in the target prompt word template, the vehicle condition description rule can be flexibly updated, that is, when the vehicle condition description rule is updated, the target prompt word template can be updated accordingly, without the need for developers to rewrite the code, and the update efficiency of the vehicle condition description rule is high and manpower is saved.

[0052] It can be understood that, since different vehicle condition configuration operations have different objectives to be achieved, that is, different tasks to be performed, correspondingly, the target prompt word templates corresponding to different vehicle condition configuration operations are also different.

[0053] To facilitate distinction, in this embodiment, the target prompt word template corresponding to the vehicle condition description generation operation is called the first prompt word template, the target prompt word template corresponding to the vehicle condition description optimization operation is called the second prompt word template, and the target prompt word template corresponding to the vehicle condition description correction operation is called the third prompt word template.

[0054] The following describes the specific process of generating a target vehicle condition description through a large language model in combination with a specific vehicle condition configuration operation.

[0055] Figure 3 A flowchart of a vehicle condition description generation method provided by an embodiment of the present invention is as follows Figure 3 As shown, the following steps may be included:

[0056] 301. In response to a vehicle condition description generation operation triggered by a user for a target vehicle, obtain vehicle configuration parameters included in vehicle information of the target vehicle uploaded by the user.

[0057] 302. Use a first prompt word template corresponding to the vehicle condition description generation operation, combined with vehicle configuration parameters, to form a first prompt word input into a large language model, so that the large language model generates a first vehicle condition description corresponding to the target vehicle according to the first prompt word.

[0058] In this embodiment, the vehicle condition configuration operation is a vehicle condition description generation operation, and the vehicle condition description generation operation corresponds to the first prompt word template. The first prompt word template includes a preset vehicle condition description rule and a task description corresponding to the vehicle condition description generation operation. For example, the task description may be: generating a first vehicle condition description that complies with the preset vehicle condition description rule according to the vehicle configuration parameters.

[0059] In a specific implementation process, in response to a vehicle condition description generation operation triggered by a user for a target vehicle, first, the vehicle configuration parameters of the target vehicle uploaded by the user and the first prompt word template are obtained. Then, the vehicle configuration parameters are combined with the first prompt word template, for example, the vehicle configuration parameters are filled into a preset position in the first prompt word template to form a first prompt word. Finally, the first prompt word is input into the large language model, so that the large language model generates a first vehicle condition description corresponding to the target vehicle according to the first prompt word.

[0060] Optionally, the first vehicle condition description may be output in a variety of ways such as voice or text, for example: the first vehicle condition description is output in Figure 2 The first vehicle condition description is displayed in the input box in the vehicle condition configuration interface shown, so that the user can confirm whether to accept the first vehicle condition description.

[0061] Optionally, if the user adopts the first vehicle condition description, the first vehicle condition description is uploaded to the used car trading platform as vehicle information, so that the used car trading platform can publish the vehicle information of the target vehicle; if the user does not adopt the first vehicle condition description, other first vehicle condition descriptions are regenerated through the large language model until the user adopts it.

[0062] In this embodiment, the large language model can automatically generate a first vehicle condition description that meets the preset vehicle condition description rules based on the vehicle configuration parameters uploaded by the user. In the process of generating the first vehicle condition description, the user can choose not to input the original vehicle condition description, which can simplify the user's operation in the process of obtaining the vehicle condition description that meets the preset vehicle condition description rules, and improve the efficiency of the user in publishing the vehicle information of the target vehicle. In addition, the first vehicle condition description generated by the large language model can clearly and indirectly express the vehicle condition information of the target vehicle, thereby improving the efficiency of other users in obtaining vehicle information from the first vehicle condition description.

[0063] Figure 4 A flowchart of another method for generating a vehicle condition description provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, the following steps may be included:

[0064] 401. In response to a vehicle condition description optimization operation triggered by a user for a target vehicle, an original vehicle condition description included in vehicle information of the target vehicle uploaded by the user is obtained.

[0065] 402. Use the second prompt word template corresponding to the vehicle condition description optimization operation and the original vehicle condition description to form a second prompt word and input it into the large language model, so that the large language model generates a second vehicle condition description optimized from the original vehicle condition description according to the second prompt word.

[0066] In this embodiment, the vehicle condition configuration operation is a vehicle condition description optimization operation, and the vehicle condition description optimization operation corresponds to the second prompt word template. The second prompt word template includes a preset vehicle condition description rule and a task description corresponding to the vehicle condition description optimization operation. For example, the task description may be: optimize the original vehicle condition description according to the preset vehicle condition description rule to generate a second vehicle condition description that meets the preset vehicle condition description rule.

[0067] In a specific implementation process, in response to a vehicle condition description optimization operation triggered by a user for a target vehicle, first, the original vehicle condition description of the target vehicle uploaded by the user and the second prompt word template are obtained. Then, the original vehicle condition description is combined with the second prompt word template, for example, the original vehicle condition description is filled into a preset position in the second prompt word template to form a second prompt word. Finally, the second prompt word is input into the large language model, so that the large language model generates a second vehicle condition description corresponding to the target vehicle according to the second prompt word.

[0068] Optionally, the second vehicle condition description may be output in various ways such as voice or text, for example: the second vehicle condition description may be output in Figure 2 The second vehicle condition description is displayed in the input box in the vehicle condition configuration interface shown, so that the user can confirm whether to accept the second vehicle condition description.

[0069] Optionally, if the user adopts the second vehicle condition description, the second vehicle condition description is uploaded to the used car trading platform as vehicle information, so that the used car trading platform can publish the vehicle information of the target vehicle; if the user does not adopt the second vehicle condition description, other second vehicle condition descriptions are regenerated through the large language model, that is, the optimization continues until the user adopts it, or the second vehicle condition description is restored to the original vehicle condition description.

[0070] In this embodiment, through the large language model, the original vehicle condition description input by the user can be optimized based on the preset vehicle condition description rules in the second prompt word to solve the problem that the original vehicle condition description does not comply with the regulations, thereby helping the user to publish the vehicle information of the target vehicle more smoothly.

[0071] Figure 5 A flowchart of another vehicle condition description generation method provided by an embodiment of the present invention is as follows: Figure 5 As shown, the following steps may be included:

[0072] 501. In response to a vehicle condition description correction operation triggered by a user for a target vehicle, an original vehicle condition description included in vehicle information of the target vehicle uploaded by the user is obtained.

[0073] 502. Use a third prompt word template corresponding to the vehicle condition description correction operation, combined with the original vehicle condition description, to form a third prompt word and input it into the large language model, so that the large language model outputs prompt information corresponding to the illegal target content in the original vehicle condition description according to the third prompt word.

[0074] 503. In response to the user modifying the original vehicle condition description according to the prompt information, the vehicle condition description of the target vehicle is determined to be the modified original vehicle condition description, or, in response to the user confirming the third vehicle condition description included in the prompt information, the vehicle condition description of the target vehicle is determined to be the third vehicle condition description; the modified original vehicle condition description and the third vehicle condition description meet the preset vehicle condition description rules.

[0075] In this embodiment, the vehicle condition configuration operation is a vehicle condition description correction operation, and the vehicle condition description correction operation corresponds to the third prompt word template. The third prompt word template includes a preset vehicle condition description rule and a task description corresponding to the vehicle condition description correction operation. For example, the task description may be: according to the preset vehicle condition description rule, find the target content that violates the regulations in the original vehicle condition description, and generate a third vehicle condition description that complies with the preset vehicle condition description rule.

[0076] It should be noted that in this solution, the vehicle condition description correction operation can be actively triggered by the user, for example: after the user enters the original vehicle condition description, the vehicle condition description correction operation is actively triggered to check the original vehicle condition description. The vehicle condition description correction operation can also be passively triggered, for example: after the user enters the original vehicle condition description, neither the vehicle condition description generation operation nor the vehicle condition description optimization operation is triggered. In this case, before the second-hand car trading platform releases the vehicle information of the target vehicle, it will call the large language model to make a compliance judgment on the original vehicle condition description, that is, trigger the vehicle condition description correction operation, so that when illegal content is found in the original vehicle condition description, it can be corrected in time to ensure the smooth release of the vehicle information of the target vehicle.

[0077] In the specific implementation process, in response to the vehicle condition description correction operation triggered by the user for the target vehicle, first, the original vehicle condition description of the target vehicle uploaded by the user and the third prompt word template are obtained. Then, the original vehicle condition description is combined with the third prompt word template, for example: the original vehicle condition description is filled into the preset position in the third prompt word template to combine into the third prompt word. Finally, the third prompt word is input into the large language model, so that the large language model outputs the prompt information corresponding to the illegal target content in the original vehicle condition description according to the third prompt word, so that the user can correct the original vehicle condition description according to the prompt information.

[0078] In an optional embodiment, the prompt information includes: the target content that violates the regulations in the original vehicle condition description. Optionally, the target content is displayed in a form that is different from other content in the original vehicle condition description, for example, by highlighting or using different font colors and other visual effects to distinguish the target content from other content in the original vehicle condition description, so that the user can quickly and accurately locate the target content that violates the regulations in the original vehicle condition description, and modify the target content so that the modified original vehicle condition description meets the preset vehicle condition description rules.

[0079] In another optional embodiment, the prompt information includes: the target content of the violation in the original vehicle condition description, and the modification suggestion corresponding to the target content. Based on the target content and the modification suggestion in the prompt information, the user can quickly modify the original vehicle condition description so that the modified original vehicle condition description complies with the preset vehicle condition description rules.

[0080] Among them, optionally, for the modified original vehicle condition description, the modified original vehicle condition description can be combined with a third prompt word template, and a new third prompt word can be regenerated and input into the large language model to make a compliance judgment on the modified original vehicle condition description through the large language model.

[0081] In another optional embodiment, the prompt information includes: a third vehicle condition description generated by the large language model that meets the preset vehicle condition description rules, that is, when the large language model determines that there is a violation of the target content in the original vehicle condition description, the third vehicle condition description is automatically generated for the user to choose whether to adopt the third vehicle condition description. Further, the third vehicle condition description can be output in multiple ways such as voice and text, for example: the third vehicle condition description is output in the Figure 2 The third vehicle condition description is displayed in an input box in the vehicle condition configuration interface shown, so that the user can confirm whether to adopt the third vehicle condition description. Optionally, if the user adopts the third vehicle condition description, in response to the user's confirmation operation on the third vehicle condition description, the vehicle condition description of the target vehicle is determined to be the third vehicle condition description, and the third vehicle condition description is uploaded to the used car trading platform as vehicle information, so that the used car trading platform can publish the vehicle information of the target vehicle.

[0082] In a specific implementation process, optionally, the large language model generates the third vehicle condition description including:

[0083] In response to a vehicle condition description correction operation triggered by a user for a target vehicle, obtaining an original vehicle condition description included in the vehicle information of the target vehicle uploaded by the user;

[0084] A third prompt word template corresponding to the vehicle condition description correction operation is used in combination with the original vehicle condition description to form a third prompt word that is input into the large language model, so that when the large language model confirms that there is illegal target content in the original vehicle condition description based on the third prompt word, a third vehicle condition description that meets preset vehicle condition description rules is generated based on the original vehicle condition description, and the third vehicle condition description is output as prompt information corresponding to the illegal target content in the original vehicle condition description.

[0085] Alternatively, in response to a vehicle condition description correction operation triggered by a user for a target vehicle, an original vehicle condition description and vehicle configuration parameters included in the vehicle information of the target vehicle uploaded by the user are obtained;

[0086] A third prompt word template corresponding to the vehicle condition description correction operation is used, combined with the original vehicle condition description and the vehicle configuration parameters, to form a third prompt word that is input into the large language model, so that when the large language model confirms that there is a violation of target content in the original vehicle condition description based on the third prompt word, a third vehicle condition description that meets preset vehicle condition description rules is generated according to the vehicle configuration parameters, and the third vehicle condition description is output as prompt information corresponding to the violation of target content in the original vehicle condition description.

[0087] Alternatively, in response to a vehicle condition description correction operation triggered by a user for a target vehicle, an original vehicle condition description and vehicle configuration parameters included in the vehicle information of the target vehicle uploaded by the user are obtained;

[0088] A third prompt word template corresponding to the vehicle condition description correction operation is used, combined with the original vehicle condition description and the vehicle configuration parameters, to form a third prompt word that is input into the large language model, so that when the large language model confirms that there is a violation of target content in the original vehicle condition description based on the third prompt word, a third vehicle condition description that meets preset vehicle condition description rules is generated based on the vehicle configuration parameters and the original vehicle condition description, and the third vehicle condition description is output as prompt information corresponding to the violation of target content in the original vehicle condition description.

[0089] In this embodiment, through the large language model, it is possible to output prompt information corresponding to the target content that violates the regulations in the original vehicle condition description based on the preset vehicle condition description rules in the third prompt word, so that the user can correct the input original vehicle condition description and solve the problem that the original vehicle condition description does not comply with the regulations, thereby helping the user to publish the vehicle information of the target vehicle more smoothly.

[0090] Based on the vehicle condition description generation method provided in the aforementioned embodiment, a vehicle condition description that meets the preset vehicle condition description rules can be obtained, which are collectively referred to as target vehicle condition descriptions for ease of expression.

[0091] It should be noted that the target vehicle condition description is different for different vehicle condition configuration operations. For example, when the vehicle condition description operation is a vehicle condition description generation operation, the target vehicle condition description is the first vehicle condition description; when the vehicle condition description operation is a vehicle condition description optimization operation, the target vehicle condition description is the second vehicle condition description; when the vehicle condition description operation is a vehicle condition description correction operation, the target vehicle condition description is the third vehicle condition description or the corrected original vehicle condition description.

[0092] Since the subsequent processing process for any vehicle condition description that meets the preset vehicle condition description rules is the same, it will not be introduced separately according to the specific vehicle condition configuration operation. Taking the target vehicle condition description as an example, a unified exemplary description of the subsequent processing process is given.

[0093] In the related art, after obtaining vehicle information such as vehicle configuration parameters and target vehicle condition description, the second-hand car trading platform can further generate and publish a picture and text post of the target vehicle based on the vehicle information and multiple vehicle appearance images uploaded by users. However, as mentioned above, the layout of such picture and text posts often has high flexibility, and users cannot quickly obtain the desired vehicle information when viewing the picture and text posts, especially when comparing and screening different vehicles. In addition, the display method of the picture and text format lacks dynamic display effects and cannot fully display the actual status of the vehicle.

[0094] In response to at least one of the above technical problems, the vehicle information processing method provided in an embodiment of the present invention improves the user's information acquisition efficiency and the display effect of vehicle information by combining the vehicle configuration parameters and target vehicle condition description in the vehicle information with the vehicle appearance image and generating an explanation video with a unified format.

[0095] Optionally, an explanation video of the target vehicle can be generated directly based on the vehicle configuration parameters, target vehicle condition description and multiple vehicle appearance images of the target vehicle uploaded by the user; or the vehicle configuration parameters, target vehicle condition description and multiple vehicle appearance images can be extracted from the generated picture and text posts of the target vehicle, and then an explanation video of the target vehicle can be generated based on the extracted vehicle configuration parameters, target vehicle condition description and multiple vehicle appearance images.

[0096] During the specific implementation process, after obtaining the vehicle configuration parameters of the target vehicle, the target vehicle condition description and multiple vehicle appearance images, firstly, the video templates corresponding to the multiple vehicle appearance images uploaded by the user are determined.

[0097] Optionally, multiple video templates corresponding to different shooting angles or shooting angle ranges may be pre-configured, wherein the video templates are configured with pre-defined animation effects, background music, subtitle formats, etc. Correspondingly, after obtaining multiple vehicle appearance images uploaded by the user, the video templates corresponding to the multiple vehicle appearance images may be determined according to the shooting angles corresponding to the multiple vehicle appearance images uploaded by the user.

[0098] Then, according to the vehicle condition configuration parameters and target vehicle condition description in the vehicle information, explanation texts are generated for each of the multiple vehicle appearance images. In layman's terms, the explanation text is an explanation of the corresponding vehicle appearance image. For example, for a vehicle appearance image taken from the front of the target vehicle, information related to the front of the vehicle can be extracted from the vehicle condition configuration parameters and target vehicle condition description, and the corresponding explanation text can be generated.

[0099] Optionally, in the process of generating the explanation copy, the highlight information in the vehicle condition configuration parameters and the target vehicle condition description can be extracted and marked, so that the highlight information can be highlighted with a prominent visual effect in the generated explanation video later. The highlight information is the advantages of the target vehicle compared with other vehicles, such as: never having a traffic accident, first-hand self-use vehicle, etc.

[0100] Finally, an explanation video corresponding to the target vehicle is generated according to the multiple vehicle appearance images, the video template and the explanation copy. Specifically, for any target vehicle appearance image among the multiple vehicle appearance images, the target vehicle appearance image and the explanation copy corresponding to the target vehicle appearance image are filled into the video template corresponding to the target vehicle appearance image to generate an explanation video corresponding to the target vehicle appearance image; the explanation videos corresponding to the multiple vehicle appearance images are spliced ​​to generate an explanation video of the target vehicle.

[0101] After generating an explanation video of the target vehicle, the used car trading platform can render and publish the explanation video for users to view.

[0102] In practical applications, multiple vehicle appearance images may include two or more vehicle appearance images with similar shooting angles. Optionally, multiple image groups corresponding to multiple vehicle appearance images may be determined first, wherein the vehicle appearance images in the same image group correspond to the same shooting angle range; then, based on the shooting angle ranges corresponding to the multiple image groups, video templates corresponding to the multiple image groups are determined; then, for any target image group in the multiple image groups, the vehicle appearance image in the target image group and the explanation text corresponding to the vehicle appearance image in the target image group are configured in the target video template corresponding to the target image group to generate an explanation video corresponding to the target image group; finally, based on the explanation videos corresponding to the multiple image groups, an explanation video corresponding to the target vehicle is generated.

[0103] Optionally, the multiple vehicle appearance images of the target vehicle uploaded by the user may also be multiple vehicle appearance videos of the target vehicle.

[0104] In this solution, the templated explanation video generation method is used to ensure the consistency of styles of different vehicles, improve the convenience of vehicle information integration, and users can quickly extract the required vehicle information from explanation videos of multiple different vehicles; and compared with the text and image output information method, the video is more intuitive and easier to understand. The method of displaying the vehicle information of the target vehicle through the explanation video can enable users to understand various aspects of the vehicle more intuitively and improve the output effect of vehicle information; in addition, the templated explanation video generation method provides an automated and efficient explanation video generation method. In actual applications, even if the appearance or vehicle information of the target vehicle changes, the video content of the explanation video can be updated in a timely and convenient manner, which can effectively improve the user experience.

[0105] In summary, in the scheme provided by the embodiment of the present invention, first, in response to the vehicle condition configuration operation triggered by the user for the target vehicle, the vehicle information of the target vehicle uploaded by the user is obtained, wherein the vehicle information is information edited by the user and may contain illegal content; then, the target prompt word template corresponding to the vehicle condition configuration operation is used, combined with the vehicle information, to form a target prompt word input into the large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description conforms to the preset vehicle condition description rules, and the content contained therein is all compliant; then, the video templates corresponding to the multiple vehicle appearance images uploaded by the user are determined, and the explanation copy of each of the multiple vehicle appearance images is generated according to the vehicle information and the target vehicle condition description; finally, the explanation video corresponding to the target vehicle is generated according to the multiple vehicle appearance images, the video template and the explanation copy. The target prompt word template corresponding to the vehicle condition configuration operation and the vehicle information uploaded by the user are combined into a target prompt word and input into the large language model, so that the large language model generates a target vehicle condition description that conforms to the preset vehicle condition description rules. Using the target vehicle condition description as the vehicle condition description for uploading to the used car trading platform can effectively avoid the failure of vehicle information release due to non-compliant vehicle condition description, thereby effectively improving the efficiency of vehicle information release. In addition, converting vehicle information, target vehicle condition description and vehicle appearance pictures into a unified format explanation video through video templates can improve the efficiency of user information acquisition.

[0106] The vehicle information processing device of one or more embodiments of the present invention will be described in detail below. Those skilled in the art will appreciate that these devices can be configured using commercially available hardware components through the steps taught in this solution.

[0107] Figure 6 A schematic diagram of the structure of a vehicle information processing device provided by an embodiment of the present invention is shown in FIG. Figure 6 As shown, the device includes: an acquisition module 11, a first processing module 12, and a second processing module 13.

[0108] The acquisition module 11 is used to obtain the vehicle information of the target vehicle uploaded by the user in response to the vehicle condition configuration operation triggered by the user for the target vehicle.

[0109] The first processing module 12 is used to use the target prompt word template corresponding to the vehicle condition configuration operation, combined with the vehicle information, to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with a preset vehicle condition description rule.

[0110] The second processing module 13 is used to determine the video templates corresponding to the multiple vehicle appearance images uploaded by the user; generate explanation texts for the multiple vehicle appearance images according to the vehicle information and the target vehicle condition description; and generate an explanation video corresponding to the target vehicle according to the multiple vehicle appearance images, the video templates and the explanation texts.

[0111] In an optional embodiment, the vehicle condition configuration operation includes a vehicle condition description generation operation, the vehicle information includes vehicle configuration parameters, and the first processing module 12 is specifically used to use the first prompt word template corresponding to the vehicle condition description generation operation, combined with the vehicle configuration parameters, to combine into a first prompt word input large language model, so that the large language model generates a first vehicle condition description corresponding to the target vehicle according to the first prompt word.

[0112] Correspondingly, the second processing module 13 is specifically configured to generate explanation texts for each of the plurality of vehicle appearance images according to the vehicle configuration parameters and the first vehicle condition description.

[0113] In an optional embodiment, the vehicle condition configuration operation includes a vehicle condition description optimization operation, the vehicle information includes an original vehicle condition description, and the first processing module 12 is specifically used to use the second prompt word template corresponding to the vehicle condition description optimization operation, combined with the original vehicle condition description, to combine into a second prompt word input into the large language model, so that the large language model generates a second vehicle condition description after optimizing the original vehicle condition description according to the second prompt word.

[0114] Correspondingly, the second processing module 13 is specifically configured to generate explanation texts for each of the plurality of vehicle appearance images according to the vehicle configuration parameters and the second vehicle condition description included in the vehicle information.

[0115] In an optional embodiment, the vehicle condition configuration operation includes a vehicle condition description correction operation, the vehicle information includes an original vehicle condition description, and the first processing module 12 is specifically used to use a third prompt word template corresponding to the vehicle condition description correction operation, combined with the original vehicle condition description, to form a third prompt word input into a large language model, so that the large language model outputs prompt information corresponding to the illegal target content in the original vehicle condition description according to the third prompt word, so that the user can correct the original vehicle condition description according to the prompt information.

[0116] In an optional embodiment, the prompt information includes: a third vehicle condition description generated by the large language model that complies with the vehicle condition description rules, and the first processing module 12 is further specifically used to respond to the user's confirmation operation on the third vehicle condition description, and determine that the vehicle condition description of the target vehicle is the third vehicle condition description.

[0117] Correspondingly, the second processing module 13 is specifically configured to generate explanation texts for each of the plurality of vehicle appearance images according to the vehicle configuration parameters and the third vehicle condition description included in the vehicle information.

[0118] In an optional embodiment, the second processing module 13 is specifically configured to determine the video templates corresponding to the multiple vehicle appearance images uploaded by the user according to the shooting angles corresponding to the multiple vehicle appearance images.

[0119] In an optional embodiment, the second processing module 13 is further specifically used to determine multiple image groups corresponding to the multiple vehicle appearance images, and the vehicle appearance images in the same image group correspond to the same shooting angle range; determine the video templates corresponding to the multiple image groups according to the shooting angle ranges respectively corresponding to the multiple image groups; generating the explanation video corresponding to the target vehicle according to the multiple vehicle appearance images, the video template and the explanation text, including: for any target image group among the multiple image groups, configuring the vehicle appearance image in the target image group and the explanation text corresponding to the vehicle appearance image in the target image group in the target video template corresponding to the target image group to generate the explanation video corresponding to the target image group; generating the explanation video corresponding to the target vehicle according to the explanation videos corresponding to the multiple image groups.

[0120] Figure 6 The device shown can execute the steps introduced in the aforementioned embodiments. For detailed execution process and technical effects, please refer to the description in the aforementioned embodiments, which will not be repeated here.

[0121] In one possible design, the above Figure 6 The structure of the vehicle information processing device shown can be implemented as an electronic device, such as Figure 7 As shown, the electronic device may include: a memory 21, a processor 22, and a communication interface 23. The memory 21 stores executable codes, and when the executable codes are executed by the processor 22, the processor 22 can at least implement the vehicle information processing method provided in the above embodiments.

[0122] In addition, an embodiment of the present invention provides a non-temporary machine-readable storage medium, on which executable code is stored. When the executable code is executed by a processor of an electronic device, the processor can at least implement the vehicle information processing method provided in the aforementioned embodiment.

[0123] An embodiment of the present invention provides a computer program product, including: a computer program, when the computer program is executed by a processor of an electronic device, the processor is caused to execute the vehicle information processing method provided in the above-mentioned embodiment.

[0124] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present invention without creative effort.

[0125] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle information processing method, characterized in that: include: In response to a vehicle condition configuration operation triggered by a user for a target vehicle, obtaining vehicle information of the target vehicle uploaded by the user; Using the target prompt word template corresponding to the vehicle condition configuration operation, combined with the vehicle information, to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with a preset vehicle condition description rule; Determine the video templates corresponding to the multiple vehicle appearance images uploaded by the user; Generating explanation texts for each of the plurality of vehicle appearance images according to the vehicle information and the target vehicle condition description; An explanation video corresponding to the target vehicle is generated according to the multiple vehicle appearance images, the video template and the explanation text.

2. The method according to claim 1, characterized in that The vehicle condition configuration operation includes a vehicle condition description generation operation, and the vehicle information includes vehicle configuration parameters; the target prompt word template corresponding to the vehicle condition configuration operation is used in combination with the vehicle information to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, including: Using the first prompt word template corresponding to the vehicle condition description generation operation, combined with the vehicle configuration parameters, to form a first prompt word input into a large language model, so that the large language model generates a first vehicle condition description corresponding to the target vehicle according to the first prompt word; Generating explanation texts for the plurality of vehicle appearance images according to the vehicle information and the target vehicle condition description includes: Generate explanation texts for each of the plurality of vehicle appearance images according to the vehicle configuration parameters and the first vehicle condition description.

3. The method according to claim 1, characterized in that The vehicle condition configuration operation includes a vehicle condition description optimization operation, and the vehicle information includes an original vehicle condition description; the target prompt word template corresponding to the vehicle condition configuration operation is used in combination with the vehicle information to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, including: Using the second prompt word template corresponding to the vehicle condition description optimization operation, combined with the original vehicle condition description, to form a second prompt word input into the large language model, so that the large language model generates a second vehicle condition description after the original vehicle condition description is optimized according to the second prompt word; Generating explanation texts for the plurality of vehicle appearance images according to the vehicle information and the target vehicle condition description includes: According to the vehicle configuration parameters included in the vehicle information and the second vehicle condition description, explanation texts for each of the multiple vehicle appearance images are generated.

4. The method according to claim 1, characterized in that: The vehicle condition configuration operation includes a vehicle condition description correction operation, and the vehicle information includes an original vehicle condition description; the target prompt word template corresponding to the vehicle condition configuration operation is used in combination with the vehicle information to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, including: A third prompt word template corresponding to the vehicle condition description correction operation is used in combination with the original vehicle condition description to form a third prompt word input into a large language model, so that the large language model outputs prompt information corresponding to the illegal target content in the original vehicle condition description according to the third prompt word, so that the user can correct the original vehicle condition description according to the prompt information.

5. The method according to claim 4, characterized in that The prompt information includes: a third vehicle condition description generated by the large language model that conforms to the vehicle condition description rule, and the user modifies the original vehicle condition description according to the prompt information, including: In response to a user's confirmation operation on the third vehicle condition description, determining that the vehicle condition description of the target vehicle is the third vehicle condition description; Generating explanation texts for the plurality of vehicle appearance images according to the vehicle information and the target vehicle condition description includes: According to the vehicle configuration parameters included in the vehicle information and the third vehicle condition description, explanation texts for each of the multiple vehicle appearance images are generated.

6. The method according to claim 1, characterized in that The determining of the video templates corresponding to the plurality of vehicle appearance images uploaded by the user includes: According to the shooting angles corresponding to the multiple vehicle appearance images uploaded by the user, video templates corresponding to the multiple vehicle appearance images are determined.

7. The method according to claim 6, characterized in that The determining, according to the shooting angles corresponding to the multiple vehicle appearance images uploaded by the user, video templates corresponding to the multiple vehicle appearance images respectively include: Determine a plurality of image groups corresponding to the plurality of vehicle appearance images, wherein the vehicle appearance images in the same image group correspond to the same shooting angle range; Determining video templates corresponding to the plurality of image groups respectively according to shooting viewing angle ranges corresponding to the plurality of image groups respectively; The step of generating an explanation video corresponding to the target vehicle according to the plurality of vehicle appearance images, the video template and the explanation text includes: For any target image group among the plurality of image groups, the vehicle appearance image in the target image group and the explanation text corresponding to the vehicle appearance image in the target image group are configured in a target video template corresponding to the target image group to generate an explanation video corresponding to the target image group; An explanation video corresponding to the target vehicle is generated according to the explanation videos respectively corresponding to the multiple image groups.

8. A vehicle information processing device, characterized in that: include: An acquisition module, configured to acquire vehicle information of a target vehicle uploaded by a user in response to a vehicle condition configuration operation triggered by a user for the target vehicle; A first processing module is used to use the target prompt word template corresponding to the vehicle condition configuration operation, combined with the vehicle information, to form a target prompt word input into a large language model, so that the large language model generates a target vehicle condition description corresponding to the target vehicle according to the target prompt word, and the target vehicle condition description complies with a preset vehicle condition description rule; A second processing module is used to determine the video templates corresponding to the multiple vehicle appearance images uploaded by the user; Generate explanation texts for each of the multiple vehicle appearance images based on the vehicle information and the target vehicle condition description; and generate an explanation video corresponding to the target vehicle based on the multiple vehicle appearance images, the video template and the explanation texts.

9. An electronic device, characterized in that: include: A memory, a processor, and a communication interface; wherein the memory stores executable code, and when the executable code is executed by the processor, the processor executes the vehicle information processing method as described in any one of claims 1 to 7.

10. A non-transitory machine-readable storage medium, characterized in that: The non-transitory machine-readable storage medium stores executable code, and when the executable code is executed by a processor of an electronic device, the processor is caused to execute the vehicle information processing method according to any one of claims 1 to 7.

Images