Project processing method and device

Abstract

The embodiment of the invention provides a project processing method and device.The project processing method comprises the steps that after security processing is conducted on a security project of a user, a security evaluation text and an evaluation score which are submitted after security processing is conducted on the security project are obtained, the security evaluation text is input into a large language model for evaluation intention recognition, and the evaluation score is obtained; and obtaining evaluation intention data, inputting the evaluation intention data into an emotion detection model for evaluation emotion detection to obtain an emotion detection result, and generating preservation evaluation data of the guarantee project according to the emotion detection result, the evaluation score and the preservation evaluation text, thereby realizing analysis and evaluation of the evaluation of the user for the preservation processing process.

Description

Technical Field

[0001] This document relates to the field of data processing technology, and in particular to a project processing method and device. Background Art

[0002] With the continuous development of information technology and the Internet, digital services have gradually been widely used in various fields. For example, in the field of security projects, with the widespread application of digital platforms such as mobile applications and mini-programs, users can access and manage security projects more conveniently. However, with the increase in the number of users and the increase in service complexity, in this case, how to effectively collect and analyze user feedback data, and how to obtain users' specific needs from massive user feedback data to improve services have become the focus of attention of all parties. Summary of the Invention

[0003] One or more embodiments of this specification provide a project processing method, including: obtaining a preservation evaluation text and evaluation score submitted after a preservation process for a security project. Inputting the preservation evaluation text into a large language model to identify evaluation intent and obtain evaluation intent data. Inputting the evaluation intent data into a sentiment detection model to detect evaluation sentiment and obtain sentiment detection results. Generating preservation evaluation data for the security project based on the sentiment detection results, the evaluation score, and the preservation evaluation text.

[0004] One or more embodiments of the present specification provide a project processing device, comprising: a data acquisition module, configured to acquire a preservation evaluation text and an evaluation score submitted after the preservation processing of a security project. An intention recognition module, configured to input the preservation evaluation text into a large language model to perform evaluation intention recognition and obtain evaluation intention data. An emotion detection module, configured to input the evaluation intention data into an emotion detection model to perform evaluation emotion detection and obtain an emotion detection result. An evaluation data generation module, configured to generate the preservation evaluation data of the security project based on the emotion detection result, the evaluation score and the preservation evaluation text.

[0005] One or more embodiments of this specification provide a project processing device, comprising: a processor; and a memory configured to store computer-executable instructions, wherein when executed, the computer-executable instructions cause the processor to: obtain a preservation evaluation text and an evaluation score submitted after the preservation processing of a security project. Input the preservation evaluation text into a large language model to perform evaluation intent recognition and obtain evaluation intention data. Input the evaluation intention data into a sentiment detection model to perform evaluation sentiment detection and obtain a sentiment detection result. Generate preservation evaluation data for the security project based on the sentiment detection result, the evaluation score, and the preservation evaluation text.

[0006] One or more embodiments of this specification provide a computer-readable storage medium for storing computer-executable instructions, which, when executed, implement the following process: obtaining a preservation evaluation text and an evaluation score submitted after the preservation processing of a security project. Inputting the preservation evaluation text into a large language model to perform evaluation intent recognition to obtain evaluation intention data. Inputting the evaluation intention data into a sentiment detection model to perform evaluation sentiment detection to obtain a sentiment detection result. Generate preservation evaluation data for the security project based on the sentiment detection result, the evaluation score, and the preservation evaluation text. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate one or more embodiments of this specification or technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments described in this specification. Those skilled in the art can derive other drawings based on these drawings without inventive effort. Figure 1 A schematic diagram of an implementation environment for a project processing method provided in one or more embodiments of this specification; Figure 2 A process flow chart of a project processing method provided for one or more embodiments of this specification; Figure 3 A flowchart of a project processing method applied to a first project processing scenario provided by one or more embodiments of this specification; Figure 4 A flowchart of a project processing method applied to a second project processing scenario provided by one or more embodiments of this specification; Figure 5 A schematic diagram of an embodiment of a project processing device provided in one or more embodiments of this specification; Figure 6 A schematic diagram of the structure of a project processing device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0008] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0009] The project processing method provided in one or more embodiments of this specification can be applied to the implementation environment of project processing. Figure 1 , the implementation environment at least includes a security data processing module 101, a large language model 102, and an emotion detection model 103; The security data processing module 101 can be used to receive and prepare security data to be processed, including security evaluation text and evaluation scores, and to generate security evaluation data by combining the evaluation intention data output by the large language model 102 and the emotion detection results output by the emotion detection model 103. The security data processing module 101 can be configured with a server cluster to support large-scale data processing and access. The large language model 102 can be used to interact with the security data processing module 101 to identify evaluation intent and generate evaluation intent data based on the security evaluation text; the emotion detection model 103 can be used to interact with the security data processing module 101 to detect evaluation emotions based on the evaluation intent data and generate emotion detection results; the large language model 102 and the emotion detection model 103 can be deployed in a server, or the large language model 102 and the emotion detection model 103 can also be deployed in a server cluster; In this implementation environment, after the user completes the preservation processing of the security project and submits the preservation evaluation text and evaluation score for the preservation processing, the preservation data processing module 101 obtains the preservation evaluation text and evaluation score submitted after the preservation processing of the security project, inputs the preservation evaluation text and evaluation score into the large language model 102, so that the large language model 102 performs evaluation intention recognition and outputs evaluation intention data, and inputs the evaluation intention data into the emotion detection model 103, so that the emotion detection model 103 performs evaluation emotion detection and outputs emotion detection results, and then generates preservation evaluation data for the security project based on the emotion detection results, evaluation scores and preservation evaluation text to improve the comprehensiveness and accuracy of the analysis and evaluation of the user's evaluation of the preservation processing process.

[0010] One or more embodiments of a project processing method provided in this specification are as follows: Reference Figure 2 The project processing method provided in this embodiment specifically includes steps S202 to S208.

[0011] Step S202: Obtain the preservation evaluation text and evaluation score submitted for the preservation process of the security project.

[0012] The protection project described in this embodiment refers to a project that provides corresponding protection services or financial compensation to the protected user after the protected user pays funds. For example, the protection project can be an insurance project. The specific protection project can be a disease protection project that provides disease protection to the protected user, such as disease insurance, or the protection project can also be an accident protection project that provides compensation for sudden accidents to the protected user, such as accident insurance. In addition, the protection project can also be a protection project that provides other protections, such as disease insurance that provides disease protection to the protected user; the protection project can also be a financial protection project, such as a savings protection project.

[0013] The preservation processing refers to the processing of changing, adjusting and / or maintaining the protection project based on the application of the protection user during the protection period of the protection project. The preservation processing can be a change in the protection details, such as the change in the protection details can be the modification of the information of the protection user of the protection project, or the increase or decrease of the insurance amount, or the change of the payment method; or the preservation processing can also be the project renewal of the protection project, such as the renewal payment service for the protection project; or the preservation processing can also be the issuance of protection resources based on the protection application submitted by the protection user, such as policy loans, claims applications, surrender services and / or policy reinstatement; or the preservation processing can also be the issuance of resources after the resource issuance conditions of the protection project are triggered, such as survival benefits, maturity benefits and / or financial compensation; here, preservation processing can also be replaced by project preservation, or preservation processing can also be replaced by project preservation processing.

[0014] Optionally, preservation processing includes at least one of the following: changes to protection details, renewal of protection projects, issuance of protection resources based on protection applications submitted by protection users, and issuance of resources after the resource issuance conditions of protection projects are triggered.

[0015] In this embodiment, after participating in the protection project, the user (protection user) can perform preservation processing on the protection project according to actual needs. Specifically, the user's preservation processing of the protection project can be achieved through various implementation methods. For example, the user can perform preservation processing of the protection project through a service subroutine, or the service platform can perform preservation processing of the user's protection project, or the user can perform preservation processing of the protection project through an offline service point of the protection project. After that, after the user completes the preservation processing of the protection project, in order to obtain the user's satisfaction with the preservation processing, a feedback channel for the preservation processing can be provided to the user, such as issuing a preservation evaluation page to the user through a service subroutine, so that the user can submit a service evaluation text and evaluation score for the preservation processing based on the preservation evaluation page.

[0016] Among them, the service subroutine refers to a subroutine that provides related services for the security project. The subroutine can be a program function module or application component installed on the client or application, or the subroutine can also be a program function module or application component loaded and installed by the client or application.

[0017] The service evaluation text refers to the text of feedback and / or opinions submitted by users on the services received. For example, the service evaluation text can be the opinions and / or feelings submitted by users on the preservation processing performed. The service evaluation text can include the evaluation and / or suggestions provided by users on service efficiency, service quality and / or service attitude; the evaluation score refers to the user's quantitative rating of the service effect through a numerical value or level. For example, the evaluation score can be the user's rating of the preservation processing based on a five-point system: 1 point (unsatisfied) to 5 points (very satisfied) after the preservation processing.

[0018] As mentioned above, the preservation processing of the security project performed by the user can be implemented in a variety of ways. For example, the user can perform the preservation processing of the security project through a service subroutine, or the service platform can perform the preservation processing of the user's security project. Accordingly, the user can submit the preservation evaluation text and evaluation score after the preservation processing; the following provides two implementation methods of performing the preservation processing of the security project and specifically explains these two implementation methods.

[0019] Implementation method 1 During the specific implementation process, in order to improve the convenience of users in performing preservation processing, preservation processing of security projects can be provided to users through a service subroutine. In an optional implementation method provided in this embodiment, preservation processing of security projects includes: performing preservation processing of security projects based on the security user accessing the security project through the service subroutine and submitting a preservation processing instruction.

[0020] Specifically, after the user accesses the protection project through the service subroutine, he or she can submit a preservation processing instruction for the protection project to perform preservation processing on the protection project, such as changing the protection details of the protection project, or renewing the protection project. After receiving the preservation processing instruction submitted by the user, the user terminal sends the preservation processing instruction, and accordingly, obtains the preservation processing instruction and performs preservation processing on the protection project according to the preservation processing instruction.

[0021] Afterwards, after the preservation processing of the security project is completed according to the preservation processing instructions, in order to obtain the user's evaluation and / or suggestions on the preservation processing, the preservation evaluation page can be displayed to the user through the service subroutine; optionally, the preservation evaluation text and evaluation score can be submitted through the preservation evaluation page displayed by the service subroutine after the preservation processing is completed.

[0022] It should be noted that the process of performing preservation processing on the security project based on the security user accessing the security project through the service subroutine and submitting preservation processing instructions can be replaced by: performing preservation processing on the security project based on the security user submitting preservation processing instructions through the service subroutine according to actual processing needs; in addition, the process of submitting the preservation evaluation text and evaluation score through the preservation evaluation page displayed by the service subroutine after the preservation processing is completed can also be replaced by: submitting through the preservation evaluation interface provided by the service subroutine after the preservation processing is completed according to actual processing needs.

[0023] Implementation method 2 During the specific implementation process, in addition to the above-mentioned user actively initiating preservation processing of the security project through the service subroutine, the service platform can also provide preservation processing of the security project to the user when the service platform detects that the preservation processing conditions are triggered. In an optional implementation method provided in this embodiment, preservation processing of the security project includes: preservation processing of the security project when the service platform detects that the preservation processing conditions of the security project are triggered.

[0024] Specifically, after the user participates in the protection project, the preservation processing conditions of the protection project can be preset on the service platform based on the project agreement of the protection project signed by the user. When it is detected that the preservation processing conditions are triggered, such as the user's insurance policy expires, the protection project in which the user participates will be preserved; optionally, the preservation processing conditions are determined based on the project agreement of the protection project signed by the protection user.

[0025] Thereafter, after the preservation processing of the security project is completed, in order to obtain the user's evaluation and / or suggestions on the preservation processing, the user can submit the evaluation and / or suggestions on the preservation processing through the preservation evaluation interface provided by the service subroutine; optionally, the preservation evaluation text and evaluation score can be submitted through the preservation evaluation interface provided by the service subroutine when the security user accesses the security project through the service subroutine.

[0026] It should be noted that the process of performing preservation processing on the protection project when the service platform detects that the preservation processing conditions of the protection project have been triggered can be replaced according to actual processing needs: the service platform performs preservation processing on the protection project based on the project agreement of the protection project signed by the protection user when it detects that the preservation processing conditions of the protection project have been triggered.

[0027] In addition, in addition to the two methods of implementing the preservation of protection projects provided above, users can also carry out the preservation of protection projects through the offline service points of the protection projects. In this case, when users carry out the preservation of protection projects through offline services, the preservation of protection projects also includes: offline preservation services provided by the protection users at the protection agencies of the protection projects.

[0028] Correspondingly, after the user receives offline preservation services from the security agency of the security project, he or she may also submit evaluations and / or suggestions on the preservation processing, such as submitting evaluations and / or suggestions on the preservation processing through the preservation evaluation interface provided by the service subroutine; optionally, the preservation evaluation text and evaluation score may be submitted through the preservation evaluation interface provided by the service subroutine when the security user accesses the security project through the service subroutine; the preservation evaluation interface is opened after it is detected that the security user receives preservation processing from the security agency of the security project.

[0029] In actual applications, after the user submits the preservation evaluation text and evaluation score for preservation processing, the insurance company may negotiate with the user to allow the user to modify the preservation evaluation text and evaluation score. In order to avoid the data inconsistency problem caused by this situation and ensure the authenticity and integrity of the preservation evaluation text and evaluation score, the preservation evaluation text and evaluation score can be uploaded to the blockchain for storage.

[0030] During the specific implementation process, after obtaining the preservation evaluation text and evaluation score submitted by the user for preservation processing, in order to ensure the transparency and security of the preservation evaluation text and evaluation score, the preservation evaluation text and evaluation score can be uploaded to the blockchain for storage; an optional implementation method provided by this embodiment also includes: uploading the preservation evaluation text and evaluation score to the blockchain for storage through the blockchain node corresponding to the service subroutine.

[0031] Step S204: input the security evaluation text into a large language model to identify evaluation intent and obtain evaluation intent data.

[0032] During specific implementation, after obtaining the preservation evaluation text submitted after the preservation processing of the security project, in order to obtain the user's true intention for the preservation processing and understand the user's specific needs and expectations, the preservation evaluation text can be further analyzed. Specifically, the preservation evaluation text is input into the large language model, so that the large language model can identify the evaluation intention and generate evaluation intention data based on the preservation evaluation text, thereby obtaining the evaluation intention data.

[0033] Among them, the large language model (LLM) refers to a pre-trained natural language model. The large language model can adopt the foundation model (Foundation Models) or the pretrained model (Pretrained Models). The architecture of the large language model can be a neural network architecture, Transform architecture or other architecture with large batch parameters. The specific large language model can directly adopt the foundation model or the pretrained model. It can also be fine-tuned on the basis of the foundation model or the pretrained model for the specific task of evaluation intent recognition (Supervised Fine-Tuning, SFT), so as to obtain a large language model that can perform the specific task of evaluation intent recognition.

[0034] During the specific implementation process, in order to improve the accuracy of identifying the user's actual intention and real needs for preservation processing and reduce misunderstandings in the analysis of the user's preservation evaluation text, the preservation evaluation text can be input into the large language model so that the large language model can identify the evaluation intention based on the preservation evaluation text. In an optional implementation provided by this embodiment, the evaluation intention identification is implemented in the following way: Perform semantic recognition on the preservation evaluation text to obtain semantic recognition results; Evaluation intention recognition is performed based on the semantic recognition results to obtain evaluation intention categories, and evaluation intention data containing the evaluation intention categories is generated.

[0035] Specifically, the large language model first performs semantic recognition on the preservation evaluation text, obtains semantic recognition results through semantic recognition, and performs evaluation intention recognition based on the semantic recognition results to roughly divide the evaluation intention expressed in the preservation evaluation text into positive intention, negative intention or neutral intention, so as to obtain evaluation intention categories and generate evaluation intention data containing evaluation intention categories.

[0036] For example, the security evaluation text submitted by a user is obtained as "The staff's attitude is very good and they solved my problem very patiently, but I am not satisfied with the overall low processing efficiency and I am disappointed with the long waiting time. I hope that the processing efficiency can be improved and the waiting time can be shortened." Semantic recognition is performed on the security evaluation text to obtain semantic recognition results containing keywords such as "good attitude", "low efficiency", "dissatisfied", and "disappointed". Evaluation intention recognition is further performed based on the semantic recognition results, and it is determined that "good attitude" is a positive intention, "low efficiency", "dissatisfied", and "disappointed" are negative intentions. Based on this, evaluation intention data containing evaluation intention categories is generated.

[0037] Step S206: input the evaluation intention data into the emotion detection model to perform evaluation emotion detection and obtain the emotion detection result.

[0038] During specific implementation, in order to more accurately analyze and evaluate the user's emotional state towards security processing, thereby understanding the customer's emotional feedback and improving the customer experience and service quality based on the customer's emotional feedback, the evaluation intention data can be further analyzed on the basis of obtaining the evaluation intention data. Specifically, the evaluation intention data is input into the emotion detection model so that the emotion detection model performs evaluation emotion detection and generates emotion detection results based on the evaluation intention data, thereby obtaining emotion detection results.

[0039] The emotion detection model refers to a model used to perform emotion detection on evaluation intention data. The emotion detection model can be a large language model, or the emotion detection model can also be an algorithm model, such as a model implemented based on a decision tree algorithm, or a model implemented based on a neural network algorithm, or a model implemented based on other algorithms; the input of the emotion detection model includes evaluation intention data, and the output includes emotion detection results.

[0040] During the specific implementation process, in order to more accurately analyze the emotional state of the preservation evaluation text submitted by the user and capture more detailed emotional changes of the user, the evaluation intention data can be further input into the emotion detection model so that the emotion detection model performs evaluation emotion detection based on the evaluation intention data. In an optional implementation provided by this embodiment, the evaluation emotion detection is implemented in the following manner: According to the emotional keywords and evaluation intention categories contained in the evaluation intention data, the evaluation emotion classification is performed to obtain the evaluation emotion category; The emotional intensity of the evaluation emotion category is identified based on the emotional keywords and contextual keywords contained in the evaluation intention data to obtain the evaluation emotion score.

[0041] The contextual keywords refer to keywords related to the expression of emotional state in the context of evaluation intention data.

[0042] Among them, in the process of evaluation emotion detection, on the basis of the above-mentioned evaluation intention identification to obtain positive intention, negative intention and / or neutral intention, the evaluation emotion classification can be further performed according to the emotion keywords and evaluation intention categories to refine the specific emotion categories, thereby obtaining the evaluation emotion categories, and then combined with the context keywords contained in the evaluation intention data, the emotion information provided by the context keywords is used to further identify the emotion intensity of the evaluation emotion category to refine the emotion intensity and obtain the evaluation emotion score.

[0043] Continuing with the above example, if "good attitude" is determined to be a positive intention and "low efficiency", "dissatisfaction" and "disappointment" are determined to be negative intentions, the evaluation sentiment classification is further performed based on the emotional keywords and evaluation intention categories contained in the evaluation intention data: based on "good attitude", the user emotion can be determined to be satisfied; based on "dissatisfaction", the user emotion can be determined to be dissatisfied; based on "disappointment", the user emotion can be determined to be disappointed. Then, the emotional intensity of the evaluation emotion category is identified in combination with the contextual keywords contained in the evaluation intention data to refine the emotional intensity and obtain the evaluation emotion score.

[0044] Step S208: Generate preservation evaluation data of the security project based on the emotion detection result, the evaluation score and the preservation evaluation text.

[0045] After obtaining the preservation evaluation text and evaluation score submitted after the preservation processing of the security project, and performing model detection based on the preservation evaluation text to obtain the emotion detection result, in this step, when multiple data including emotion detection results, evaluation scores and / or preservation evaluation texts are obtained, in order to integrate the multiple data, preservation evaluation data is generated based on the emotion detection results, evaluation scores and preservation evaluation texts.

[0046] During specific implementation, in order to improve the accuracy and comprehensiveness of the service quality assessment of preservation processing, multiple data such as emotion detection results, evaluation scores and / or preservation evaluation texts can be combined to generate a more comprehensive preservation evaluation. Specifically, preservation evaluation data for the security project is generated based on the emotion detection results, evaluation scores and preservation evaluation texts.

[0047] In a specific implementation process, an optional implementation provided by this embodiment generates preservation evaluation data for a security project based on the emotion detection result, the evaluation score, and the preservation evaluation text, including: The sentiment detection results, preservation evaluation text and evaluation scores are input into the evaluation fusion model to fuse the evaluation data and obtain the preservation evaluation data.

[0048] The evaluation fusion model is used to perform data fusion on multiple data, such as evaluation data fusion of sentiment detection results, preservation evaluation text and evaluation scores; the input of the evaluation fusion model includes sentiment detection results, preservation evaluation text and / or evaluation scores, and the output of the evaluation fusion model includes preservation evaluation data.

[0049] Specifically, in order to quantify the user's overall evaluation of the preservation process and obtain the user's suggestions for improvement of the preservation process, evaluation data fusion can be performed based on the sentiment detection results, evaluation scores, and preservation evaluation text to generate preservation evaluation data for the security project. In an optional implementation provided in this embodiment, the evaluation data fusion includes: Calculate the preservation score based on the evaluation score and the evaluation sentiment score included in the sentiment detection result; Suggested keywords for preservation processing are extracted from the preservation evaluation text, and the obtained suggested keywords and preservation scores are used as preservation evaluation data.

[0050] Continuing with the above example, the user submits a preservation evaluation text and gives an evaluation score of x points. Based on the evaluation sentiment score y points obtained above, the preservation score can be calculated according to the preset weight formula (the preset evaluation score accounts for a%, and the evaluation sentiment score accounts for b%). The preservation score is: x*a%+y*b%, and the recommended keywords for preservation processing of the preservation evaluation text are extracted, and "improve processing efficiency" and "shorten waiting time" are extracted as recommended keywords. Based on this, the generated preservation evaluation data includes the preservation score and recommended keywords.

[0051] In actual applications, when users are carrying out preservation processing for security projects, the preservation processing may involve multiple steps or links. In this case, in order to conduct in-depth analysis of the preservation evaluations submitted by users to determine the nodes or links with problems in the preservation processing process, in addition to quantifying the user's overall evaluation of the preservation processing and obtaining improvement suggestions, attribution analysis can also be used to determine the problematic links or abnormal points in the preservation processing process. In another optional implementation method provided by this embodiment, the evaluation data fusion includes: Calculate the preservation score based on the evaluation score and the evaluation sentiment score included in the sentiment detection result; Extract the recommended keywords for preservation processing of the preservation evaluation text to obtain the recommended keywords, Perform attribution analysis based on the suggested keywords, the evaluation emotion categories contained in the emotion detection results, and the corresponding processing flow nodes to obtain abnormal process nodes in the preservation processing process; The recommended keywords, security scores, and abnormal process nodes are used as security evaluation data.

[0052] For example, after obtaining the security score and the suggested keywords "improve processing efficiency" and "shorten waiting time", we further conduct attribution analysis based on the suggested keywords, combined with the negative emotion categories in the emotion detection results, and specific processing process nodes, such as information entry, information review and / or notification. It is determined that the "review stage" is the main reason for low processing efficiency (abnormal process node). Based on this, the obtained suggested keywords, security scores, and abnormal process nodes are used as security evaluation data.

[0053] It should be noted that the above-mentioned implementation method of evaluation data fusion can execute any one or both of them according to the actual processing needs during the specific implementation process, for example: evaluation data fusion includes: calculating the preservation score according to the evaluation score and the evaluation emotion score contained in the emotion detection result, and using the preservation score as the preservation evaluation data; for another example, evaluation data fusion includes: extracting the recommended keywords for preservation processing of the preservation evaluation text, and obtaining the recommended keywords, Attribution analysis is performed based on the suggested keywords, the evaluation emotion categories contained in the emotion detection results, and the corresponding processing flow nodes to obtain the abnormal process nodes of the preservation processing flow; the suggested keywords and abnormal process nodes are used as preservation evaluation data; this embodiment will not be described in detail here.

[0054] In practical applications, after obtaining preservation evaluation data based on user-submitted preservation evaluation texts and scores, the preservation process can be optimized based on this data to continuously improve and optimize the quality of preservation services and increase user satisfaction with subsequent preservation processes. Optionally, the preservation evaluation data can be used to optimize the preservation process for the security project.

[0055] In the specific implementation process, an optional implementation method provided by this embodiment optimizes the preservation processing process of the security project, which is implemented in the following manner: The preservation evaluation data is input into the preservation process optimization model to perform process optimization analysis and processing of the preservation processing process of the security project, and obtain the process optimization strategy of the preservation processing process.

[0056] The preservation process optimization model refers to a model used to analyze preservation evaluation data to generate a process optimization strategy for the preservation processing process; the input of the preservation process optimization model includes the preservation evaluation data, and the output includes the process optimization strategy for the preservation processing process.

[0057] Specifically, after obtaining the preservation evaluation data, the preservation evaluation data is input into the preservation process optimization model. The preservation process optimization model performs process optimization analysis and processing of the preservation processing process of the security project based on the preservation evaluation data to identify the problems and causes of the preservation processing process pointed to by the preservation evaluation data, thereby obtaining a process optimization strategy for the preservation processing process. Thereafter, the preservation processing process can be improved and optimized based on the process optimization strategy.

[0058] To sum up, the present embodiment provides a project processing method. After the user performs preservation processing on a security project and submits a preservation evaluation text and evaluation score for the preservation processing through a service subroutine, the method first obtains the preservation evaluation text and evaluation score submitted after the preservation processing of the security project. Secondly, the preservation evaluation text is input into a large language model for evaluation intention recognition to obtain evaluation intention data, so as to obtain the user's true intention for the preservation processing and understand the user's specific needs and expectations. Then, in order to more accurately analyze and evaluate the user's emotional state for the preservation processing, thereby understanding the customer's emotional feedback, the evaluation intention data is further input into the emotion detection model, so that the emotion detection model performs evaluation emotion detection and generates emotion detection results based on the evaluation intention data, thereby obtaining emotion detection results. Finally, when multiple data including emotion detection results, evaluation scores and preservation evaluation texts are obtained, in order to improve the comprehensiveness of the service quality evaluation of the preservation processing, preservation evaluation data of the security project is generated based on the emotion detection results, evaluation scores and preservation evaluation texts, thereby improving the comprehensiveness and accuracy of the analysis and evaluation of the user's evaluation of the preservation processing process.

[0059] The following takes the application of a project processing method provided in this embodiment in the first project processing scenario as an example, combined with Figure 3 , for further explanation of the project processing method provided in this embodiment, see Figure 3 , the project processing method applied to the first project processing scenario specifically includes the following steps.

[0060] Step S302: Obtain the preservation evaluation text and evaluation score submitted after the preservation process of the security project.

[0061] Among them, the preservation evaluation text and evaluation score are submitted through the preservation evaluation page displayed by the service subroutine after the preservation processing is completed, or the preservation evaluation text and evaluation score are submitted through the preservation evaluation interface provided by the service subroutine when the user accesses the protection project through the service subroutine.

[0062] Step S304: perform semantic recognition on the preservation evaluation text to obtain a semantic recognition result.

[0063] Step S306 , performing evaluation intention recognition based on the semantic recognition result to obtain the evaluation intention category, and generating evaluation intention data including the evaluation intention category.

[0064] Step S308: performing evaluation emotion classification based on the emotion keywords and evaluation intention categories contained in the evaluation intention data to obtain evaluation emotion categories.

[0065] Step S310 , identifying the emotional intensity of the evaluation emotional category based on the emotional keywords and the contextual keywords included in the evaluation intention data to obtain an evaluation emotional score.

[0066] Step S312: Calculate the preservation score based on the evaluation score and the evaluation emotion score included in the emotion detection result.

[0067] Step S314: extracting recommended keywords for preservation processing from the preservation evaluation text.

[0068] Step S316: Generate preservation evaluation data for the security project based on the obtained suggested keywords and preservation scores.

[0069] After step S316 is executed, the preservation evaluation data may be input into the preservation process optimization model to perform process optimization analysis and processing of the preservation processing process of the guarantee project, thereby obtaining a process optimization strategy for the preservation processing process.

[0070] It should be noted that any one of steps S302 to S316 or any combination of multiple steps can be combined with any one of steps S202 to S208 to form a new implementation method according to the needs of implementation deployment; in addition, according to the needs of actual deployment, any one or multiple technical features can be selected from steps S302 to S316 and combined with any one or multiple technical features provided by steps S202 to S208 to form a new implementation method; or, any one or multiple technical features in steps S302 to S316 can be replaced with any one or multiple technical features provided by steps S202 to S208 to form a new implementation method according to the needs of actual deployment, which will not be repeated here.

[0071] The following takes the application of a project processing method provided in this embodiment in the second project processing scenario as an example, combined with Figure 4 , for further explanation of the project processing method provided in this embodiment, see Figure 4 , the project processing method applied to the second project processing scenario specifically includes the following steps.

[0072] Step S402: Obtain the preservation evaluation text and evaluation score submitted after the preservation process of the security project.

[0073] Among them, the preservation evaluation text and evaluation score are submitted through the preservation evaluation page displayed by the service subroutine after the preservation processing is completed, or the preservation evaluation text and evaluation score are submitted through the preservation evaluation interface provided by the service subroutine when the user accesses the protection project through the service subroutine.

[0074] Step S404: perform semantic recognition on the preservation evaluation text to obtain a semantic recognition result.

[0075] Step S406 , performing evaluation intention recognition based on the semantic recognition result to obtain an evaluation intention category, and generating evaluation intention data including the evaluation intention category.

[0076] Step S408: input the evaluation intention data into the emotion detection model to perform evaluation emotion detection, and obtain an emotion detection result containing the evaluation emotion category.

[0077] Step S410 : extracting suggested keywords for preservation processing from the preservation evaluation text to obtain suggested keywords.

[0078] Step S412: performing attribution analysis based on the suggested keywords, the evaluation emotion categories included in the emotion detection results, and the corresponding processing flow nodes to obtain abnormal process nodes of the preservation processing flow.

[0079] In step S414, the suggested keywords and abnormal process nodes are used as security evaluation data.

[0080] After step S414 is executed, the preservation evaluation data may be input into the preservation process optimization model to perform process optimization analysis and processing of the preservation processing process of the guarantee project, thereby obtaining a process optimization strategy for the preservation processing process.

[0081] It should be noted that any one of steps S402 to S414 or any combination of multiple steps can be combined with any one of steps S202 to S208 to form a new implementation method according to the needs of implementation deployment; in addition, according to the needs of actual deployment, any one or multiple technical features can be selected from steps S402 to S414 and combined with any one or multiple technical features provided by steps S202 to S208 to form a new implementation method; or, any one or multiple technical features in steps S402 to S414 can be replaced with any one or multiple technical features provided by steps S202 to S208 to form a new implementation method according to the needs of actual deployment, which will not be repeated here.

[0082] An embodiment of a project processing device provided in this specification is as follows: In the above embodiment, a project processing method is provided, and correspondingly, a project processing device is also provided, which will be described below with reference to the accompanying drawings.

[0083] Reference Figure 5 , which shows a schematic diagram of an embodiment of a project processing device provided by this embodiment.

[0084] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiment described below is only illustrative.

[0085] This embodiment provides a project processing device, the device comprising: The data acquisition module 502 is configured to acquire the preservation evaluation text and evaluation score submitted after the preservation process of the security project; Intention recognition module 504 is configured to input the security evaluation text into a large language model to perform evaluation intention recognition and obtain evaluation intention data; The emotion detection module 506 is configured to input the evaluation intention data into the emotion detection model to perform evaluation emotion detection and obtain an emotion detection result; The evaluation data generation module 508 is configured to generate the preservation evaluation data of the security project according to the emotion detection result, the evaluation score and the preservation evaluation text.

[0086] An embodiment of a project processing device provided in this specification is as follows: Corresponding to the project processing method described above, based on the same technical concept, one or more embodiments of this specification further provide a project processing device, which is used to execute the project processing method provided above. Figure 6 A schematic diagram of the structure of a project processing device provided in one or more embodiments of this specification.

[0087] This embodiment provides a project processing device, including: like Figure 6 As shown, the project processing device may vary significantly due to different configurations or performance, and may include one or more processors 601 and memory 602. The memory 602 may store one or more applications or data. The memory 602 may be either ephemeral or persistent. The applications stored in the memory 602 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the project processing device. Furthermore, the processor 601 may be configured to communicate with the memory 602 to execute the series of computer-executable instructions in the memory 602 on the project processing device. The project processing device may also include one or more power supplies 603, one or more wired or wireless network interfaces 604, one or more input / output interfaces 605, one or more keyboards 606, and the like.

[0088] In a specific embodiment, the project processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the project processing device, and the one or more programs are configured to be executed by one or more processors, including computer-executable instructions for performing the following: Obtain the preservation evaluation text and evaluation score submitted after the preservation treatment of the security project; Inputting the security evaluation text into a large language model to identify evaluation intent and obtain evaluation intent data; Inputting the evaluation intention data into the emotion detection model to perform evaluation emotion detection and obtain the emotion detection result; The preservation evaluation data of the security project is generated according to the emotion detection result, the evaluation score and the preservation evaluation text.

[0089] An embodiment of a computer-readable storage medium provided in this specification is as follows: Corresponding to the project processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a computer-readable storage medium.

[0090] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions. When the computer-executable instructions are executed, the following process is implemented: Obtain the preservation evaluation text and evaluation score submitted after the preservation treatment of the security project; Inputting the security evaluation text into a large language model to identify evaluation intent and obtain evaluation intent data; Inputting the evaluation intention data into the emotion detection model to perform evaluation emotion detection and obtain the emotion detection result; The preservation evaluation data of the security project is generated according to the emotion detection result, the evaluation score and the preservation evaluation text.

[0091] It should be noted that the embodiment of a computer-readable storage medium in this specification and the embodiment of a work identification and processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned corresponding method, and the repeated parts will not be repeated.

[0092] An embodiment of a computer program product provided in this specification is as follows: Corresponding to the project processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a computer program product.

[0093] A computer program product comprising a computer program / instructions, which, when executed by a processor, implements the following steps: Obtain the preservation evaluation text and evaluation score submitted after the preservation treatment of the security project; Inputting the security evaluation text into a large language model to identify evaluation intent and obtain evaluation intent data; Inputting the evaluation intention data into the emotion detection model to perform evaluation emotion detection and obtain the emotion detection result; The preservation evaluation data of the security project is generated according to the emotion detection result, the evaluation score and the preservation evaluation text.

[0094] It should be noted that the embodiment of a computer program product in this specification and the embodiment of a work identification and processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned corresponding method, and the repeated parts will not be repeated.

[0095] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. For example, the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments are similar to the method embodiments, so the description is relatively simple. For relevant content in the device embodiments, equipment embodiments, computer-readable storage medium embodiments, and computer program product embodiments, please refer to the partial description of the method embodiments.

[0096] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] In the 1930s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using physical hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly performed using software called a "logic compiler." This is similar to the software compilers used during program development. Before compilation, the original code must be written in a specific programming language, called a Hardware Description Language (HDL). There are many types of HDL, including ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that simply by programming a method flow in one of these hardware description languages ​​and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0098] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the memory control logic. Those skilled in the art will also appreciate that, in addition to implementing the controller purely in computer-readable program code, the controller can also be implemented in the form of logic gates, switches, an application-specific integrated circuit, a programmable logic controller, an embedded microcontroller, etc. by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the means for implementing the various functions included therein can also be considered as structures within the hardware component. Alternatively, the means for implementing the various functions can be considered both a software module implementing the method and a structure within the hardware component.

[0099] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0100] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0101] Those skilled in the art will appreciate that one or more embodiments of this specification may be provided as a method, system, or computer program product. Thus, one or more embodiments of this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable work recognition processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable work recognition processing device generate instructions for implementing the processes in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable work recognition processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable work recognition processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0106] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0107] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising at least one ..." does not exclude the presence of additional identical elements in the process, method, commodity, or apparatus comprising the element.

[0109] One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0110] The foregoing description is merely an example of the present invention and is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of the claims herein.

Claims

1. A project processing method comprising: Obtain the preservation evaluation text and evaluation score submitted after the preservation treatment of the security project; Inputting the security evaluation text into a large language model to identify evaluation intent and obtain evaluation intent data; Inputting the evaluation intention data into the emotion detection model to perform evaluation emotion detection and obtain the emotion detection result; The preservation evaluation data of the security project is generated according to the emotion detection result, the evaluation score and the preservation evaluation text.

2. The project processing method according to claim 1, wherein the security project preservation processing comprises: Performing preservation processing on the protection item according to the preservation processing instruction submitted by the protection user accessing the protection item through the service subroutine; The preservation evaluation text and the evaluation score are submitted through the preservation evaluation page displayed by the service subroutine after the preservation process is completed.

3. The project processing method according to claim 1, wherein the security project preservation processing comprises: Performing preservation processing on the security item when the service platform detects that the preservation processing condition of the security item is triggered; The preservation processing conditions are determined based on the project agreement of the protection project signed by the protection user; The security evaluation text and the evaluation score are submitted through the security evaluation interface provided by the service subroutine when the security user accesses the security project through the service subroutine.

4. The project processing method according to claim 1, wherein the evaluation intention identification is implemented in the following manner: Performing semantic recognition on the preservation evaluation text to obtain a semantic recognition result; Evaluation intention recognition is performed based on the semantic recognition result to obtain an evaluation intention category, and the evaluation intention data containing the evaluation intention category is generated.

5. The project processing method according to claim 1, wherein the evaluation sentiment detection is implemented in the following manner: According to the emotional keywords and evaluation intention categories contained in the evaluation intention data, evaluation emotion classification is performed to obtain evaluation emotion categories; The emotional intensity of the evaluation emotional category is identified based on the emotional keywords and the contextual keywords included in the evaluation intention data to obtain an evaluation emotional score.

6. The project processing method according to claim 1, wherein generating the preservation evaluation data of the security project based on the emotion detection result, the evaluation score, and the preservation evaluation text comprises: Inputting the emotion detection result, the security evaluation text and the evaluation score into an evaluation fusion model to perform evaluation data fusion to obtain the security evaluation data; The preservation evaluation data is used to optimize the preservation processing flow of the security project.

7. The project processing method according to claim 6, wherein the evaluation data fusion comprises: Calculating a preservation score based on the evaluation score and the evaluation emotion score included in the emotion detection result; Suggested keywords for preservation processing are extracted from the preservation evaluation text, and the obtained suggested keywords and the preservation score are used as the preservation evaluation data.

8. The project processing method according to claim 6, wherein the optimization of the preservation processing flow of the security project is achieved by: The preservation evaluation data is input into a preservation process optimization model to perform process optimization analysis on the preservation processing process of the security project, and a process optimization strategy for the preservation processing process is obtained.

9. According to the project processing method according to claim 1, the preservation processing includes at least one of the following: changes in protection details, project renewal of the protection project, issuance of protection resources based on the protection application submitted by the protection user, and resource issuance after the resource issuance conditions of the protection project are triggered.

10. The project processing method according to claim 1, wherein the security evaluation text and the evaluation score are submitted through the security evaluation interface provided by the service subroutine when the security user accesses the security project through the service subroutine; The security evaluation interface is opened after it is detected that the security user has performed security processing at the security organization of the security project.

11. The project processing method according to claim 10, further comprising: The preservation evaluation text and the evaluation score are uploaded to the blockchain for storage through the blockchain node corresponding to the service subroutine.

12. A project processing device comprising: A data acquisition module is configured to acquire the preservation evaluation text and evaluation score submitted after the preservation processing of the security project; An intention recognition module is configured to input the security evaluation text into a large language model to perform evaluation intention recognition and obtain evaluation intention data; An emotion detection module is configured to input the evaluation intention data into an emotion detection model to perform evaluation emotion detection and obtain an emotion detection result; An evaluation data generation module is configured to generate preservation evaluation data of the security project based on the emotion detection result, the evaluation score and the preservation evaluation text.

13. An item processing device comprising: processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to: Obtain the preservation evaluation text and evaluation score submitted after the preservation treatment of the security project; Inputting the security evaluation text into a large language model to identify evaluation intent and obtain evaluation intent data; Inputting the evaluation intention data into the emotion detection model to perform evaluation emotion detection and obtain the emotion detection result; The preservation evaluation data of the security project is generated according to the emotion detection result, the evaluation score and the preservation evaluation text.

14. A computer-readable storage medium for storing computer-executable instructions, wherein the computer-executable instructions implement the steps of the method of claim 1 when executed.

Images