Program update evaluation method, related device, equipment and storage medium

Abstract

The invention discloses a program updating evaluation method, a related device, equipment and a storage medium, and the method comprises the steps: obtaining a current version of a target program on current equipment in response to a to-be-updated target version of the target program on the current equipment; generating evaluation data under a plurality of evaluation dimensions at least based on the difference between the published data of the current version and the published data of the target version; wherein the evaluation data under each evaluation dimension respectively represents the change degree of the target version relative to the current version of the target program on the current equipment under the corresponding evaluation dimension; and based on the evaluation data under the plurality of evaluation dimensions, generating an update evaluation summary of the target program. According to the scheme, the update evaluation summary about the target program as accurate as possible can be provided, the personalized requirement for deciding whether to update the target program is met, and the use feeling of a user is improved.

Description

Technical Field

[0001] The present application relates to the field of program processing technology, and in particular to a program update evaluation method and related devices, equipment and storage media. Background Art

[0002] With the development of information technology, program developers will adapt to their own development needs, constantly update the content of various programs in applications and systems, and generate new versions.

[0003] In the prior art, the version update of each program is usually implemented based on the manual selection of the user. However, in actual application scenarios, due to the large number of programs and the high frequency of updates, users cannot quickly determine whether the updated content meets their personal needs, which further causes users to encounter unnecessary updates or miss important updates, reducing the user experience of the program update function. In view of this, how to meet the personalized needs of deciding whether to update the target program to improve the user experience of the target program update function has become an urgent problem to be solved. Summary of the invention

[0004] The main technical problem solved by the present application is to provide a program update evaluation method and related devices, equipment and storage media, which can provide an update evaluation summary of the target program as accurate as possible, meet the personalized needs of deciding whether to update the target program, and enhance the user's experience of the target program update function.

[0005] In order to solve the above technical problems, the first aspect of the present application provides a program update evaluation method, including: in response to the existence of a target version to be updated of the target program on the current device, obtaining the current version of the target program on the current device; generating evaluation data under several evaluation dimensions based at least on the difference between the release data of the current version and the release data of the target version; wherein the evaluation data under each evaluation dimension respectively represents: the degree of change of the target version of the target program on the current device compared with the current version under the corresponding evaluation dimension; based on the evaluation data under several evaluation dimensions, generating an update evaluation summary of the target program.

[0006] In order to solve the above technical problems, the second aspect of the present application provides a program update evaluation device, including: an acquisition module, a generation module and an evaluation module, the acquisition module is used to obtain the current version of the target program on the current device in response to the existence of a target version to be updated of the target program on the current device; the generation module is used to generate evaluation data under several evaluation dimensions based on at least the difference between the release data of the current version and the release data of the target version; wherein the evaluation data under each evaluation dimension respectively represents: the degree of change of the target version of the target program on the current device compared with the current version under the corresponding evaluation dimension; the evaluation module is used to generate an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions.

[0007] In order to solve the above technical problems, the third aspect of the present application provides an electronic device, including a memory and a processor coupled to each other, the memory storing program instructions, and the processor being used to execute the program instructions to implement the program update evaluation method in the above first aspect.

[0008] In order to solve the above technical problem, the fourth aspect of the present application provides a computer-readable storage medium, which stores program instructions that can be executed by a processor, and the program instructions are used to implement the program update evaluation method described in the first aspect above.

[0009] In the above scheme, when there is a target version to be updated in the target program on the current device, the current version of the target program on the current device is obtained, and evaluation data under several evaluation dimensions are generated based on at least the difference between the release data of the current version and the release data of the target version, and the evaluation data under each evaluation dimension respectively represent: the change degree of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension, and the update evaluation summary of the target program is generated based on the evaluation data under several evaluation dimensions. Therefore, the evaluation data under several evaluation dimensions can reflect the change of the target program from the current version to the target version from as many angles as possible, and can provide as concise and critical update information as possible by generating an evaluation summary. In addition, in the update evaluation process, the objective situation of the current device itself is used as a benchmark, rather than the general situation of the general public. It can start from the actual situation of the current version of the target program on the current device, and meet the personalized needs of deciding whether to update the target program as much as possible. Therefore, it can provide an update evaluation summary about the target program as accurate as possible, meet the personalized needs of deciding whether to update the target program, and enhance the user's sense of use of the target program update function. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of an embodiment of an update evaluation method of the present application program; Figure 2It is a schematic diagram of an embodiment of an update evaluation report of the update evaluation method of the present application program; Figure 3 is a flowchart of another embodiment of the update evaluation method of the application program; Figure 4 It is a schematic diagram of the framework of an embodiment of an update evaluation device of the present application program; Figure 5 It is a schematic diagram of the framework of an embodiment of the electronic device of the present application; Figure 6 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0011] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0012] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0013] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0014] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the fragment " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" in this article means two or more than two.

[0015] See also Figure 1 , Figure 1 This is a flowchart of an embodiment of the application program update evaluation method. Specifically, it may include the following steps: Step S10: In response to the target version to be updated existing in the target program on the current device, the current version of the target program on the current device is obtained.

[0016] In the disclosed embodiments, the specific types of the current device and the target program are not limited in this application. For example, the target device is a server, a smart phone, a laptop computer, an intelligent mechanical device, etc., and the target program is an application program, a system program, etc.

[0017] In an implementation scenario, the version information of the target program can be detected through an API (Application Programming Interface) call, or the program version can be detected through the built-in update mechanism of the operating system. If there is a target version to be updated in the target program on the current device, the current version of the target program on the current device can be obtained.

[0018] In one implementation scenario, in response to the existence of a target version to be updated of the target program on the current device, after obtaining the current version of the target program on the current device, several user comments on the target version are obtained. It should be noted that the acquisition of user comments has been authorized by the acquisition authority of relevant users, devices, systems, etc., and the acquisition source of user comments is not limited in this application. For example, the target program is located in the comment area of ​​the application store, the comment area of ​​the social media account about the target program, etc., and statistical analysis is performed based on several user comments to obtain the satisfaction of the target program being updated to the target version. When the satisfaction is greater than a preset threshold, the step of generating evaluation data under several evaluation dimensions based on at least the difference between the release data of the current version and the release data of the target version is executed. The above scheme uses the satisfaction obtained based on the statistical analysis of user comments as a pre-judgment condition for whether to execute the evaluation data of several evaluation dimensions, which can filter out the target program that cannot meet the needs of most users when updated to the target version, and reduce the pressure of data processing while satisfying the user's demand for updating the target program as much as possible.

[0019] In a specific implementation scenario, the satisfaction with the target program being updated to the target version includes a satisfaction rating. For example, the satisfaction rating includes "good", "medium", and "poor".

[0020] In a specific implementation scenario, the rating values ​​of several user reviews on the target program being updated to the target version are obtained, and the average of the several rating values ​​is calculated as the satisfaction with the target program being updated to the target version. For example, a five-point system is used in the user reviews to score the target program being updated to the target version. There are five users who scored the target program being updated to the target version as 4.1, 3.5, 3, 4, and 2.1, respectively. The calculated satisfaction is 3.34.

[0021] In a specific implementation scenario, the preset threshold is a fixed value set by the developer based on prior experience. For example, in the case of a five-point scoring system, the preset threshold is set to 2. Alternatively, the preset threshold is a dynamically adjusted value and is related to data such as the program type of the target program, the number of user reviews, and the source of user reviews.

[0022] In a specific implementation scenario, when the satisfaction with the target program being updated to the target version is a satisfactory rating, the preset threshold is a preset satisfactory rating, for example, "poor" is used as the preset threshold, that is, "good" and "medium" are greater than the preset threshold.

[0023] In a specific implementation scenario, as a possible implementation method, a preset threshold generation model can be pre-trained, and the preset threshold generation model can include but is not limited to the network model of the Encoder-Decoder architecture, etc. In order to ensure the generation accuracy of the preset threshold generation model as much as possible, the attribute information of the sample program sample version can be collected, and the attribute information includes the program type of the sample program, the number of user comments of the sample program updated to the sample version, the source of the user comments, etc., and the real threshold is marked on the sample program sample version. On this basis, the attribute information of the sample program sample version can be processed based on the preset threshold generation model to obtain the predicted threshold of the sample program sample version, so that the network parameters of the preset threshold generation model can be adjusted based on the difference between the real threshold and the predicted threshold until the preset threshold generation model training converges, and the attribute information of the target program updated to the target version can be processed based on the preset threshold generation model that has converged training to obtain the preset threshold. It should be noted that the specific processing process of the preset threshold generation model can refer to the technical details such as the network model of the Encoder-Decoder architecture, which will not be repeated here.

[0024] In a specific implementation scenario, when the satisfaction level is no more than a preset threshold, the comment content about the target program to the target version is obtained from several user comments. For example, the comment content may include text content, picture content, audio content, etc. Specifically, the picture content is emoticons, etc. It can be understood that a certain comment content may be unimodal content or multimodal content, and several user comments may contain comment content of different modalities. The comment content is summarized based on the large language model to generate update question text about the target version of the target program.

[0025] In a specific implementation scenario, the large language model can understand human multimodal natural language input, and obtain keyword information about the input content and the logical relationship between each element based on the input content, and generate semantically relevant output. For specific principles, please refer to more technical details of the large language model, which will not be repeated here. It should be noted that the large language model may include but is not limited to: LLAMA, Bloom and other open source large models. The network architecture of the large language model is not limited here. The large language model in this application can be an open source large model or a finished large model after parameter adjustment. The specific application is not limited. For example, the comments include comment A "Frequent crashes or flashbacks after updates, resulting in inability to use normally", comment B "Extremely unstable after updates, often flashing", comment C "Incompatible with the system after update, so it keeps flashing and cannot be used at all", comment D "Not as good as before", and comment E "The phone gets very hot after the update, which greatly affects the user experience. It is recommended not to update". Comments A, B, C, D, and E are input into the large language model together to obtain a content summary of the comments by the large language model, and generate an update question text about the target version of the target program: "After updating to the target version, the target program may have problems such as frequent crashes, flashbacks, and device heating. It is recommended to carefully consider whether to update the target program."

[0026] Step S20: Generate evaluation data under several evaluation dimensions based at least on the difference between the published data of the current version and the published data of the target version.

[0027] In the disclosed embodiment, the evaluation data under each evaluation dimension respectively represents: the target program on the current device under the corresponding evaluation dimension, the degree of change of the target version compared to the current version, and the evaluation data under several evaluation dimensions can reflect the change of the target program from the current version to the target version from as many angles as possible. It should be noted that the number and specific dimensions of the evaluation dimensions are not limited in this application.

[0028] In one implementation scenario, when several evaluation dimensions include interface change, the published data includes an example interface, and the evaluation data under the interface change dimension is determined based on the similarity between the example interface of the current version and the example interface of the target version.

[0029] In a specific implementation scenario, when the example interface includes several interface images, evaluation data under the dimension of interface change amount is obtained based on the similarity between the example interface of the current version and the example interface of the target version belonging to the same function interface. For example, the release data of the current version includes the current function 1 interface, the current function 2 interface, and the current function 3 interface, and the release data of the target version includes the target function 1 interface, the target function 2 interface, and the target function 3 interface. A first similarity is obtained based on the similarity between the current function 1 interface and the target function 1 interface, a second similarity is obtained based on the similarity between the current function 2 interface and the target function 2 interface, and a third similarity is obtained based on the similarity between the current function 3 interface and the target function 3 interface. Evaluation data under the dimension of interface change amount is obtained based on the average value of the first similarity, the second similarity, and the third similarity.

[0030] In a specific implementation scenario, a weight factor may be assigned to the similarity obtained for each functional interface according to parameter information such as the importance and usage frequency of different functional interfaces, thereby improving the accuracy of evaluation data under the dimension of interface change.

[0031] In a specific implementation scenario, the degree of change of the target version compared to the current version in the interface change dimension includes a change rating and / or a change value. For example, the change rating includes "large", "medium" and "small", and the change value includes the percentage value of the similarity between the example interface of the current version and the target version.

[0032] In one implementation scenario, when several evaluation dimensions include update data volume, the published data includes data packet size, and the evaluation data under the update data volume dimension is determined based on the data volume difference between the data packet size of the current version and the data packet size of the target version.

[0033] In a specific implementation scenario, the degree of change of the target version compared to the current version in the dimension of updated data volume includes a change rating and / or a change value. For example, the change rating includes "large", "medium" and "small", and the change value includes the difference in data packet size between the current version and the target version.

[0034] In an implementation scenario, when several evaluation dimensions include the scope of update content, the released data includes update notes. For example, the update notes of the target version include "1. Fixed known system vulnerabilities and issues, and improved system stability and security. 2. Added new functions and optimized existing functions, improved system usability and user experience. 3. Updated relevant data and information to ensure the data integrity and accuracy of the system." When the current version and the target version of the target program are two adjacently released versions, the update notes of the target version are summarized to obtain evaluation data under the dimension of update content scope.

[0035] In another implementation scenario, when the current version and the target version of the target program are not two adjacently released versions, based on the release data of each historical version between the current version and the target version, the update description of each historical version is obtained, and based on the update description of the current version, the update description of the target version, and the update description of each historical version, an update summary is obtained to determine the evaluation data under the update content scope dimension. The above scheme uses the release data of each historical version between the current version and the target version on the update content scope as reference information for generating evaluation data under the update content scope dimension, which can further provide the most accurate update information about the target program, meet the personalized needs of deciding whether to update the target program, and enhance the user's sense of use of the target program update function.

[0036] In a specific implementation scenario, the update summary of the target version compared to the current version in the update content scope dimension includes a change rating and / or a scope summary text, for example, the change rating includes "large", "medium" and "small".

[0037] In a specific implementation scenario, the version number corresponding to the current version of the target program on the current device is obtained, and the version number corresponding to the target version of the target program on the current device is obtained. The version number is the identification number of the target program version, which can be used to identify the functions and facilities provided by the corresponding version. Since the version number usually includes a major version number, a minor version number, a revision number, and a build number, etc., it can represent the changes in major versions, the addition of functional modules, the number of revisions to a certain version, the number of times the program is built or compiled, etc., so the update history, functional changes, and repaired defects of the current version and the target version of the target program can be obtained based on a short symbolic identifier. Based on the difference in identifiers between the current version and the target version, the version update status of each historical version between the current version and the target version can be quickly obtained. Based on the difference in version numbers between the current version and the target version, it is determined whether the current version and the target version of the target program are two adjacently released versions, which can reduce the pressure of data processing and improve the accuracy of the target program update information.

[0038] In one implementation scenario, the degree of change of the target version compared to the current version includes a change rating and a change value, and the update evaluation summary is specifically generated from the change rating. Before generating the update evaluation summary of the target program based on the evaluation data under several evaluation dimensions, the degree of change of each evaluation dimension and the configuration control are displayed on the current device, and when the configuration instruction is executed on the configuration control, the change rating of the evaluation dimension to which the configuration control belongs is adjusted. For example, the degree of change under the dimension of the change amount of the display interface on the current device is specifically "small" and "30%", and the configuration control A corresponding to the dimension of the change amount of the display interface, in response to the configuration instruction of the configuration control A, adjusts the change rating to "medium". The above scheme can meet the personalized needs of different users, provide an update evaluation summary of the target program that is as accurate as possible, and enhance the user's sense of use of the target program update function.

[0039] In a specific implementation scenario, the change rating is generated by a large language model based on the change value. For the specific principle, please refer to more technical details of the large language model, which will not be repeated here.

[0040] In a specific implementation scenario, the change rating of the evaluation dimension to which the adjusted configuration control belongs, as well as the change value under the evaluation dimension to which the configuration control belongs are obtained, and based on the mapping relationship between the change rating and the change value, reference information for indicating the degree of change generated by the large language model under the evaluation dimension is generated. For example, still taking the aforementioned embodiment as an example, the mapping relationship between the change value "30%" and the change rating "medium" is obtained. When it is detected that a candidate program different from the target program has a version to be updated, the mapping relationship between the change value "30%" under the display interface change dimension and the change rating "medium" is used as reference information for generating the degree of change of the candidate program under the display interface change dimension. This can meet the personalized needs of different users, provide an update evaluation summary of the target program that is as accurate as possible, and enhance the user's sense of use of the target program update function.

[0041] Step S30: Generate an updated evaluation summary of the target program based on the evaluation data under several evaluation dimensions.

[0042] In an implementation scenario, an update evaluation summary of the target program is generated based on the evaluation data under several evaluation dimensions. Therefore, the evaluation data under several evaluation dimensions can reflect the changes of the target program from the current version to the target version from as many angles as possible, and by generating the evaluation summary, it is possible to provide the most concise and critical update information. In addition, in the update evaluation process, the objective situation of the current device itself is used as a benchmark, rather than the general situation of the general public. Starting from the actual situation of the current version of the target program on the current device, it is possible to meet the personalized needs of deciding whether to update the target program as much as possible. Therefore, it is possible to provide an update evaluation summary of the target program that is as accurate as possible, meet the personalized needs of deciding whether to update the target program, and enhance the user's sense of use of the target program update function.

[0043] In an implementation scenario, based on the evaluation data under several evaluation dimensions, a prompt instruction is constructed, the prompt instruction is used to instruct the large language model to refer to the evaluation data under several evaluation dimensions to generate an update risk prompt of the target program under at least one evaluation dimension, the prompt instruction is input into the large language model to obtain the update risk prompt under at least one evaluation dimension, and based on the update risk prompt under each evaluation dimension, an update evaluation summary of the target program is generated. For example, the evaluation data obtained under the interface change amount dimension is "large", and the evaluation data obtained under the update data amount dimension is "small", and an update risk prompt under the interface change amount evaluation dimension is obtained, "The interface has undergone a significant change after the update, which may affect your operating habits", and based on the update risk prompt under each evaluation dimension, an update evaluation summary of the target program is generated, "The interface has undergone a significant change after the update, which may affect your operating habits, but according to user evaluations, most users reflect that the updated interface is more in line with daily usage habits, and you can refer to it for updating". It should be noted that the construction of the prompt instruction can refer to more technical details of the large language model, which will not be repeated here.

[0044] See also Figure 2 , Figure 2 This is a schematic diagram of an embodiment of an update evaluation report of the application program update evaluation method. Figure 2As shown, in an implementation scenario, after generating an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions, an update evaluation report of the target program is generated based on the evaluation data under several evaluation dimensions and the update evaluation summary of the target program, and the update evaluation report is displayed on the current device to guide the user of the current device whether to update the target program. In the above scheme, the evaluation data under several evaluation dimensions can reflect the changes of the target program from the current version to the target version from as many angles as possible, and the generated update evaluation summary can provide the most concise and critical update information. Therefore, it is possible to provide an update evaluation summary of the target program that is as accurate as possible, thereby enhancing the user's sense of use of the target program update function.

[0045] In a specific implementation scenario, taking the aforementioned embodiment as an example, when the satisfaction level is not greater than a preset threshold, an update question text about the target version of the target program is generated based on a content summary of the review content based on a large language model, and an update evaluation report about the target program is generated based on the update question text.

[0046] In a specific implementation scenario, in response to the existence of target versions to be updated of several target programs on the current device, an update evaluation report corresponding to each target program is generated, and then each update evaluation report is summarized to obtain a report summary and displayed on the current device.

[0047] In the above scheme, when there is a target version to be updated in the target program on the current device, the current version of the target program on the current device is obtained, and evaluation data under several evaluation dimensions are generated based on at least the difference between the release data of the current version and the release data of the target version, and the evaluation data under each evaluation dimension respectively represent: the change degree of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension, and the update evaluation summary of the target program is generated based on the evaluation data under several evaluation dimensions. Therefore, the evaluation data under several evaluation dimensions can reflect the change of the target program from the current version to the target version from as many angles as possible, and can provide as concise and critical update information as possible by generating an evaluation summary. In addition, in the update evaluation process, the objective situation of the current device itself is used as a benchmark, rather than the general situation of the general public. It can start from the actual situation of the current version of the target program on the current device, and meet the personalized needs of deciding whether to update the target program as much as possible. Therefore, it can provide an update evaluation summary about the target program as accurate as possible, meet the personalized needs of deciding whether to update the target program, and enhance the user's sense of use of the target program update function.

[0048] See also Figure 3 , Figure 3This is a flowchart of another embodiment of the update evaluation method of the application program. Specifically, it may include the following steps: Step S10: In response to the target version to be updated existing in the target program on the current device, the current version of the target program on the current device is obtained.

[0049] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0050] Step S11: Perform statistical analysis based on several user comments to obtain satisfaction with the target program being updated to the target version.

[0051] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0052] Step S12: Determine whether the satisfaction level is greater than a preset threshold.

[0053] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0054] Step S40: In response to the satisfaction level not being greater than a preset threshold, a content summary of the review content based on the large language model is generated to generate an update question text about the target version of the target program.

[0055] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0056] Step S21: In response to the satisfaction being greater than a preset threshold, based on the similarity between the example interface of the current version and the example interface of the target version, determining evaluation data under the dimension of interface change amount.

[0057] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0058] Step S22: In response to the satisfaction being greater than a preset threshold, based on the data volume difference between the data package size of the current version and the data package size of the target version, determining the evaluation data under the update data volume dimension.

[0059] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0060] Step S23: In response to the satisfaction being greater than a preset threshold, an update summary is obtained based on the update description of the current version, the update description of the target version, and the update descriptions of each historical version to determine evaluation data under the update content scope dimension.

[0061] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0062] Step S30: Generate an updated evaluation summary of the target program based on the evaluation data under several evaluation dimensions.

[0063] For details, please refer to the aforementioned embodiments, which will not be described again here for the sake of brevity.

[0064] In the above scheme, when there is a target version to be updated in the target program on the current device, the current version of the target program on the current device is obtained, and evaluation data under several evaluation dimensions are generated based on at least the difference between the release data of the current version and the release data of the target version, and the evaluation data under each evaluation dimension respectively represent: the change degree of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension, and the update evaluation summary of the target program is generated based on the evaluation data under several evaluation dimensions. Therefore, the evaluation data under several evaluation dimensions can reflect the change of the target program from the current version to the target version from as many angles as possible, and can provide as concise and critical update information as possible by generating an evaluation summary. In addition, in the update evaluation process, the objective situation of the current device itself is used as a benchmark, rather than the general situation of the general public. It can start from the actual situation of the current version of the target program on the current device, and meet the personalized needs of deciding whether to update the target program as much as possible. Therefore, it can provide an update evaluation summary about the target program as accurate as possible, meet the personalized needs of deciding whether to update the target program, and enhance the user's sense of use of the target program update function.

[0065] See also Figure 4 , Figure 4 40 is a schematic diagram of a framework of an embodiment of the present application program update evaluation device 40. Figure 4 As shown, the program update evaluation device 40 includes: an acquisition module 41, a generation module 42 and an evaluation module 43, wherein the acquisition module 41 is used to obtain the current version of the target program on the current device in response to the existence of a target version to be updated of the target program on the current device; the generation module 42 is used to generate evaluation data under several evaluation dimensions based on at least the difference between the release data of the current version and the release data of the target version; wherein the evaluation data under each evaluation dimension respectively characterizes: the degree of change of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension; the evaluation module 43 is used to generate an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions.

[0066] In the above scheme, the program update evaluation device 40 obtains the current version of the target program on the current device when there is a target version to be updated in the target program on the current device, generates evaluation data under several evaluation dimensions at least based on the difference between the release data of the current version and the release data of the target version, and the evaluation data under each evaluation dimension respectively represent: the change degree of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension, and generates an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions. Therefore, the evaluation data under several evaluation dimensions can reflect the change of the target program from the current version to the target version from as many angles as possible, and can provide as concise and critical update information as possible by generating an evaluation summary. In addition, in the update evaluation process, the objective situation of the current device itself is used as a benchmark, rather than the general situation of the general public. It can start from the actual situation of the current version of the target program on the current device, and meet the personalized needs of deciding whether to update the target program as much as possible. Therefore, it can provide an update evaluation summary about the target program as accurate as possible, meet the personalized needs of deciding whether to update the target program, so as to enhance the user's sense of use of the target program update function.

[0067] In some disclosed embodiments, the evaluation module 43 also includes a prompt construction module (not shown) for constructing prompt instructions based on evaluation data under several evaluation dimensions; wherein the prompt instructions are used to instruct the large language model to generate an update risk prompt for the target program under at least one evaluation dimension with reference to the evaluation data under several evaluation dimensions; the evaluation module 43 also includes a prompt input module (not shown) for inputting the prompt instructions into the large language model to obtain an update risk prompt under at least one evaluation dimension; the evaluation module 43 also includes an evaluation summary module (not shown) for generating an update evaluation summary of the target program based on the update risk prompts under each evaluation dimension.

[0068] In some disclosed embodiments, after generating an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions, the program update evaluation device 40 also includes a report generation module (not shown) for generating an update evaluation report of the target program based on the evaluation data under several evaluation dimensions and the update evaluation summary of the target program; the program update evaluation device 40 also includes a report display module (not shown) for displaying the update evaluation report on the current device to guide the user of the current device whether to update the target program.

[0069] In some disclosed embodiments, the degree of change of the target version compared to the current version includes a change rating and a change amount value, and the update evaluation summary is specifically generated from the change rating. Before generating an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions, the program update evaluation device 40 also includes a data display module (not shown) for displaying the degree of change and configuration controls of each evaluation dimension on the current device; the program update evaluation device 40 also includes a rating configuration module (not shown) for adjusting the change rating of the evaluation dimension to which the configuration control belongs in response to a configuration instruction for the configuration control.

[0070] In some disclosed embodiments, the change rating is generated by the large language model based on the change value, and the program update evaluation device 40 also includes an adjustment acquisition module (not shown) for acquiring the change rating of the evaluation dimension to which the adjusted configuration control belongs, and the change value under the evaluation dimension to which the configuration control belongs; the program update evaluation device 40 also includes a reference information module (not shown) for generating reference information indicating the degree of change generated by the large language model under the evaluation dimension based on the mapping relationship between the change rating and the change value.

[0071] In some disclosed embodiments, when several evaluation dimensions include the amount of interface change, the published data includes an example interface, and the generation module 42 also includes a first data module (not shown) for determining the evaluation data under the dimension of the amount of interface change based on the similarity between the example interface of the current version and the example interface of the target version; and / or, when several evaluation dimensions include the amount of updated data, the published data includes the data packet size, and the generation module 42 also includes a second data module (not shown) for determining the evaluation data under the dimension of the amount of updated data based on the difference in data volume between the data packet size of the current version and the data packet size of the target version.

[0072] In some disclosed embodiments, when several evaluation dimensions include the scope of update content, the published data includes update instructions, and the generation module 42 also includes a description acquisition module (not shown) for obtaining the update instructions for each historical version based on the published data of each historical version between the current version and the target version; the generation module 42 also includes a third data module (not shown) for obtaining an update summary based on the update instructions of the current version, the update instructions of the target version, and the update instructions of each historical version to determine the evaluation data under the dimension of update content scope.

[0073] In some disclosed embodiments, in response to the existence of a target version to be updated of the target program on the current device, after obtaining the current version of the target program on the current device, and before generating evaluation data under several evaluation dimensions based at least on the difference between the release data of the current version and the release data of the target version, the program update evaluation device 40 also includes a comment acquisition module (not shown) for obtaining several user comments on the target version; the program update evaluation device 40 also includes a statistical analysis module (not shown) for performing statistical analysis based on the several user comments to obtain satisfaction with the target program being updated to the target version; the program update evaluation device 40 also includes a satisfaction judgment module (not shown) for executing the step of generating evaluation data under several evaluation dimensions based at least on the difference between the release data of the current version and the release data of the target version in response to the satisfaction being greater than a preset threshold.

[0074] In some disclosed embodiments, when the satisfaction level is not greater than a preset threshold, the program update evaluation device 40 further includes a comment content acquisition module (not shown) for acquiring comment content about a target program to a target version from a number of user comments; the program update evaluation device 40 further includes a comment content summary module (not shown) for summarizing the comment content based on a large language model to generate an update question text about the target program to the target version.

[0075] See also Figure 5 , Figure 5 1 is a schematic diagram of a framework of an embodiment of an electronic device 50 of the present application. The electronic device 50 includes a memory 51 and a processor 52. The memory 51 stores program instructions, and the processor 52 is used to execute the program instructions to implement the steps in any of the above-mentioned program update evaluation method embodiments. For details, please refer to the aforementioned disclosed embodiments, which will not be repeated here. The electronic device 50 may specifically include but is not limited to: a server, a smart phone, a laptop computer, a tablet computer, a self-service machine, etc., which are not limited here.

[0076] Specifically, the processor 52 is used to control itself and the memory 51 to implement the steps in any of the above-mentioned program update evaluation method embodiments. The processor 52 can also be called a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with signal processing capabilities. The processor 52 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 52 can be implemented by an integrated circuit chip.

[0077] In the above scheme, when there is a target version to be updated in the target program on the current device, the electronic device 50 obtains the current version of the target program on the current device, generates evaluation data under several evaluation dimensions at least based on the difference between the release data of the current version and the release data of the target version, and the evaluation data under each evaluation dimension respectively represent: the change degree of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension, and generates an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions. Therefore, the evaluation data under several evaluation dimensions can reflect the change of the target program from the current version to the target version from as many angles as possible, and can provide as concise and critical update information as possible by generating an evaluation summary. In addition, in the update evaluation process, the objective situation of the current device itself is used as a benchmark, rather than the general situation of the general public. It can start from the actual situation of the current version of the target program on the current device, and meet the personalized needs of deciding whether to update the target program as much as possible. Therefore, it can provide an update evaluation summary about the target program as accurate as possible, meet the personalized needs of deciding whether to update the target program, so as to enhance the user's sense of use of the target program update function.

[0078] See also Figure 6 , Figure 6 The schematic diagram is a schematic diagram of a computer-readable storage medium 60 of the present application. The computer-readable storage medium 60 stores program instructions 61 that can be executed by a processor, and the program instructions 61 are used to implement the steps in any of the above-mentioned program update evaluation method embodiments.

[0079] In the above scheme, the computer-readable storage medium 60 obtains the current version of the target program on the current device when there is a target version to be updated in the target program on the current device, generates evaluation data under several evaluation dimensions at least based on the difference between the release data of the current version and the release data of the target version, and the evaluation data under each evaluation dimension respectively represent: the target program on the current device under the corresponding evaluation dimension, the change degree of the target version compared with the current version, and generates an update evaluation summary of the target program based on the evaluation data under several evaluation dimensions. Therefore, the evaluation data under several evaluation dimensions can reflect the change of the target program from the current version to the target version from as many angles as possible, and can provide as concise and critical update information as possible by generating an evaluation summary. In addition, in the update evaluation process, the objective situation of the current device itself is used as a benchmark, rather than the general situation of the general public. It can start from the actual situation of the current version of the target program on the current device, and meet the personalized needs of deciding whether to update the target program as much as possible. Therefore, it can provide an update evaluation summary about the target program as accurate as possible, meet the personalized needs of deciding whether to update the target program, so as to enhance the user's sense of use of the target program update function.

[0080] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0081] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0082] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0083] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0084] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

Claims

1. A program update evaluation method, characterized in that: include: In response to the target program on the current device having a target version to be updated, obtaining a current version of the target program on the current device; At least based on the difference between the release data of the current version and the release data of the target version, generate evaluation data under several evaluation dimensions; wherein the evaluation data under each evaluation dimension respectively represents: the degree of change of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension; Based on the evaluation data under the several evaluation dimensions, an updated evaluation summary of the target program is generated.

2. The method according to claim 1, characterized in that: The step of generating an evaluation summary about the target program update content based on the evaluation data under the plurality of evaluation dimensions includes: Based on the evaluation data under the several evaluation dimensions, construct a prompt instruction; wherein the prompt instruction is used to instruct the large language model to refer to the evaluation data under the several evaluation dimensions to generate an update risk prompt for the target program under at least one of the evaluation dimensions; Inputting the prompt instruction into the large language model to obtain an updated risk prompt under at least one of the evaluation dimensions; Based on the update risk prompts under each of the evaluation dimensions, an update evaluation summary of the target program is generated.

3. The method according to claim 1, characterized in that After generating an updated evaluation summary of the target program based on the evaluation data under the plurality of evaluation dimensions, the method further includes: Based on the evaluation data under the plurality of evaluation dimensions and the updated evaluation summary of the target program, generating an updated evaluation report of the target program; The update evaluation report is displayed on the current device to guide the user of the current device whether to update the target program.

4. The method according to claim 1, characterized in that: The degree of change of the target version compared to the current version includes a change rating and a change amount value, and the update evaluation summary is specifically generated from the change rating. Before generating the update evaluation summary of the target program based on the evaluation data under the multiple evaluation dimensions, the method includes: Displaying the degree of change of each evaluation dimension and configuration controls on the current device; In response to a configuration instruction for the configuration control, a change rating of the evaluation dimension to which the configuration control belongs is adjusted.

5. The method according to claim 4, characterized in that The change rating is generated by a large language model based on the change value, and the method further includes: Obtaining the change rating of the evaluation dimension to which the configuration control belongs after adjustment, and the change amount value under the evaluation dimension to which the configuration control belongs; Based on the mapping relationship between the change rating and the change amount value, reference information is generated to indicate the degree of change generated by the large language model under the evaluation dimension.

6. The method according to claim 1, characterized in that In the case where the plurality of evaluation dimensions include an amount of interface change, the published data includes an example interface, and the generating of the evaluation data under the plurality of evaluation dimensions based at least on a difference between the published data of the current version and the published data of the target version includes: Determining evaluation data under the interface change amount dimension based on the similarity between the example interface of the current version and the example interface of the target version; And / or, in the case where the several evaluation dimensions include the amount of updated data, the published data includes a data packet size, and the generating of the evaluation data under the several evaluation dimensions based at least on the difference between the published data of the current version and the published data of the target version includes: Based on the data volume difference between the data packet size of the current version and the data packet size of the target version, the evaluation data under the update data volume dimension is determined.

7. The method according to claim 1, characterized in that In the case where the plurality of evaluation dimensions include an update content range, the release data includes an update description, and the generating of the evaluation data under the plurality of evaluation dimensions based at least on the difference between the release data of the current version and the release data of the target version includes: Based on the release data of each historical version between the current version and the target version, obtaining update descriptions of each historical version; Based on the update description of the current version, the update description of the target version, and the update descriptions of each historical version, an update summary is obtained to determine the evaluation data under the update content scope dimension.

8. The method according to claim 1, characterized in that In response to the target version to be updated of the target program on the current device, after obtaining the current version of the target program on the current device, and before generating evaluation data under a plurality of evaluation dimensions based at least on the difference between the published data of the current version and the published data of the target version, the method further includes: Obtaining a number of user reviews of the target version; Performing statistical analysis based on the plurality of user comments to obtain satisfaction with respect to updating the target program to the target version; In response to the satisfaction being greater than a preset threshold, the step of generating evaluation data under a plurality of evaluation dimensions based at least on the difference between the published data of the current version and the published data of the target version is performed.

9. The method according to claim 8, characterized in that When the satisfaction level is not greater than the preset threshold, the method further includes: Obtaining review contents about the target program to the target version from the plurality of user reviews; Based on the content summary of the review content by the large language model, an updated question text about the target version of the target program is generated.

10. A program update evaluation device, characterized in that: include: An acquisition module, configured to acquire a current version of the target program on the current device in response to a target version to be updated existing in the target program on the current device; A generating module, configured to generate evaluation data under a plurality of evaluation dimensions based at least on the difference between the release data of the current version and the release data of the target version; wherein the evaluation data under each evaluation dimension respectively represents: the degree of change of the target version compared with the current version of the target program on the current device under the corresponding evaluation dimension; An evaluation module is used to generate an updated evaluation summary of the target program based on the evaluation data under the plurality of evaluation dimensions.

11. An electronic device, characterized in that: It comprises a memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the program update evaluation method according to any one of claims 1 to 9.

12. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the program update evaluation method according to any one of claims 1 to 9 is implemented.

Images