Evaluation report generation method and device, medium and program product

Abstract

The invention discloses an evaluation report generation method and device, a medium and a program product. The method relates to the technical field of big data, and comprises the steps of obtaining a key information image of a third-party user according to an identifier of the third-party user; identifying text data in the key information image through an OCR (Optical Character Recognition) technology, and establishing an association relationship between the text data and the data class; according to an association relationship between the text data and the data class, generating an evaluation result of the plurality of evaluation indexes; and obtaining a target evaluation report template according to the third-party user attribute, and filling the target evaluation report template by using the evaluation result. By adopting the technical scheme, the multi-source data can be comprehensively integrated to accurately evaluate the third-party user, the evaluation report can be quickly generated, and the comprehensiveness and accuracy of information in the evaluation report can be ensured.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to an evaluation report generation method, device, medium and program product. Background Art

[0002] In the business process of an enterprise, in order to facilitate decision-makers to evaluate and review third-party users, business personnel are often required to directly provide third-party user evaluation reports to decision-makers for review.

[0003] In the existing technology, business personnel generally analyze and summarize the original data and then generate an evaluation report.

[0004] The generation requirement of an assessment report is to ensure that the information is detailed and accurate. However, for large-scale enterprises, the amount of original data is very large. If data analysis and assessment report generation are performed manually, it is difficult to comprehensively integrate multi-source data for accurate assessment while ensuring data privacy. The assessment takes a long time, and the generated electronic report lacks in-depth interactive display of special information. Summary of the Invention

[0005] The present invention provides an evaluation report generation method, device, medium and program product, which can comprehensively integrate multi-source data to accurately evaluate third-party users, quickly generate evaluation reports, and ensure the comprehensiveness and accuracy of the information in the evaluation reports.

[0006] According to one aspect of the present invention, a method for generating an evaluation report is provided, comprising:

[0007] Obtaining a key information image of the third-party user based on the third-party user's identifier;

[0008] Use OCR technology to identify text data in key information images and establish the association between text data and data classes;

[0009] Generate evaluation results of multiple evaluation indicators based on the association relationship between text data and data classes;

[0010] According to the third-party user attributes, a target assessment report template is obtained, and the target assessment report template is filled with the assessment results.

[0011] Optionally, establish an association between text data and data classes, including:

[0012] Semantically encode text data and generate text vectors;

[0013] Match the text vector with a predefined key information template to obtain a similarity score; the key information template includes a description of the key information semantic features of the specified data class and regular expression matching rules;

[0014] When the similarity score between the text vector of the target text and the target key information template is higher than the preset score, the target text is determined as key information, and an association relationship is established between the target text and the corresponding data class according to the data class to which the target key information template belongs.

[0015] The advantage of this setting is that it can reduce the interference of non-key data in the text data directly recognized by OCR. By adding the semantic feature description of key information in the key information template, it can determine whether the text belongs to the key information of a certain data class from the semantic level, avoiding the limitation of relying solely on surface text matching. By adding regular expression matching rules to the key information template, it can quickly filter the text from the grammatical structure level, supplement the deficiencies of semantic matching, and improve the accuracy of key information extraction.

[0016] Optionally, based on the association between text data and data classes, generate evaluation results for multiple evaluation indicators, including:

[0017] When the evaluation index is a data evaluation index, determining first text data for data calculation according to a calculation rule of the target data and an association relationship between the text data and the data class;

[0018] generating calculation results of target data based on the first text data, and arranging the calculation results of the target data according to time periods;

[0019] Based on the sorted calculation results, trend analysis charts and data descriptions are generated.

[0020] The advantage of this setting is that by organizing the calculation results by time period in the evaluation results and generating charts, the data change trend can be intuitively displayed, the readability of the data can be improved, and by generating data descriptions, the business logic behind the data can be explained, lowering the decision-making threshold.

[0021] Optionally, based on the association between text data and data classes, generate evaluation results for multiple evaluation indicators, including:

[0022] When the evaluation indicator is a grade evaluation indicator, determining second text data for grade evaluation based on data factors required for grade evaluation and an association relationship between text data and data classes;

[0023] The second text data is input into a pre-trained evaluation model to obtain the evaluation score and evaluation grade output by the evaluation model, and a grade evaluation description is generated based on the evaluation score and evaluation grade; wherein the weight of each grade evaluation item is pre-set in the evaluation model, and the weight of each grade evaluation item is obtained based on a pre-constructed judgment matrix, which includes scores of multiple expert users on each grade evaluation item.

[0024] The advantage of this setting is that the judgment matrix can be used to integrate the experience and judgment of multiple experts, obtain weights that are closer to the actual evaluation criteria, reduce subjective bias, thereby improving the evaluation accuracy of the evaluation model and ensuring the rationality of the evaluation scores and evaluation results.

[0025] Optionally, after generating evaluation results of multiple evaluation indicators based on the association between text data and data classes, the following steps are further included:

[0026] Conduct outlier drilldown analysis on the evaluation results of each evaluation indicator;

[0027] When an outlier is detected in the target evaluation result of the target evaluation indicator, an outlier analysis description and a solution strategy are generated for the outlier;

[0028] Generate an analysis file of the target evaluation results based on the target text data, outlier analysis description, and solution strategy used in the target evaluation indicator evaluation process, and establish an association relationship between the target evaluation result identifier and the analysis file;

[0029] Store the analysis file in cloud storage, generate an access link based on the storage location of the analysis file, and add a user signature to the access link.

[0030] The advantage of this setting is that an analysis file can be directly generated for the outliers based on the evaluation results. The analysis file clearly defines the causes and solutions of the outliers, provides credibility support for the outliers, and can fine-grainedly control data access rights to prevent data leakage.

[0031] Optionally, after filling the target assessment report template with the assessment results, the following steps are further included:

[0032] If there are outliers in the target evaluation results, an analysis file associated with the target evaluation results is determined, and an access link to the analysis file is added to the evaluation report.

[0033] The benefit of this setting is that by actively associating and embedding the access link of the analysis file, the analysis process of the outliers is directly presented to the report user, and at the same time a reference solution is provided to the user, thereby improving the user's decision-making time and improving business efficiency within the enterprise.

[0034] Optionally, after obtaining the key information image of the third-party user according to the identifier of the third-party user and recognizing text data in the key information image using OCR technology, the method further includes:

[0035] Generate a hash value for each key information image collected, and package the hash value of the key information image, data metadata, and collection number to generate a transaction;

[0036] The legitimacy of the transaction is verified based on the smart contract pre-deployed on the blockchain. If the transaction passes the verification, it is determined to be a legal transaction;

[0037] Generate an identifier for a legitimate transaction and record the legitimate transaction in the distributed ledger of the blockchain; the identifier of the legitimate transaction includes the timestamp of the legitimate transaction and the hash value of the previous block.

[0038] The advantage of this setting is that by adding hash values ​​and using hash values ​​for verification, it can be ensured that the data has not been tampered with throughout the entire process from collection to chain upload. By adding the timestamp of the legal transaction and the hash value of the previous block in the identifier of the legal transaction, it can be ensured that the current transaction is closely linked to the previous block, ensuring the continuity and traceability of the data. By recording legal transactions in the distributed ledger, the distributed ledger can be maintained by all nodes in the network. Even if a single point is offline, it can still be guaranteed that data will not be lost. Verification through smart contracts can avoid future time or obviously erroneous time records, ensuring the legality and compliance of the data.

[0039] According to another aspect of the present invention, an electronic device is provided, comprising:

[0040] at least one processor; and

[0041] a memory communicatively connected to the at least one processor; wherein,

[0042] The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to execute the evaluation report generating method described in any embodiment of the present invention.

[0043] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the evaluation report generation method described in any embodiment of the present invention when executed.

[0044] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the evaluation report generation method according to any embodiment of the present invention is implemented.

[0045] The technical solution of the embodiment of the present invention facilitates early data collection and later data storage by obtaining the key information image of the third-party user based on the identification of the third-party user. By using OCR technology, text data is identified in the key information image, and the association relationship between the text data and the data class is established. This can reduce the interference of non-key data in the text data directly identified by OCR, and facilitate the subsequent efficient acquisition of evaluation results. By generating evaluation results of multiple evaluation indicators based on the association relationship between the text data and the data class, obtaining the target evaluation report template according to the third-party user attributes, and using the evaluation results to fill in the target evaluation report template, multi-source data can be fully integrated to accurately evaluate the third-party user, and an evaluation report can be quickly generated. The comprehensiveness and accuracy of the information in the evaluation report can be guaranteed, and the problem that manual generation of evaluation reports is time-consuming and the accuracy of the report cannot be guaranteed.

[0046] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 This is a flowchart of a method for generating an evaluation report according to a first embodiment of the present invention;

[0049] Figure 2 is a flowchart of another method for generating an evaluation report provided according to the second embodiment of the present invention;

[0050] Figure 3 This is a schematic diagram of the structure of an evaluation report generating device provided in accordance with a third embodiment of the present invention;

[0051] Figure 4 It is a structural diagram of an electronic device for implementing the evaluation report generation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0053] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] Example 1

[0055] Figure 1 This is a flowchart of an evaluation report generation method provided in Example 1 of the present invention. This embodiment is applicable to the situation of generating evaluation reports for third-party users. The method can be executed by an evaluation report generation device. The evaluation report generation device can be implemented in the form of hardware and / or software and can generally be configured in a computer or processor with data processing and image processing functions.

[0056] like Figure 1 As shown, the method includes:

[0057] S110 : Acquire a key information image of the third-party user according to the identifier of the third-party user.

[0058] Optionally, the third-party user may refer to an entity that needs to be evaluated, such as a company with a cooperative relationship, etc. The third-party user identifier may refer to a unique identifier used to identify the third-party user, such as company name, organization code and other information.

[0059] It should be noted that the information collected in the present invention is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse; at the same time, provide users with corresponding operation entrances for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0060] Optionally, key information images of third-party users can be collected through channels such as internal enterprise platforms, industry news websites, or databases actively provided by third-party users, public resource center systems, etc. All collected data are data authorized for use by third-party users or data that is publicly available on the entire network.

[0061] Optionally, in order to facilitate early data collection and later data storage, key information images of third-party users can be directly collected, such as scanned images of documents, screenshots of web pages, etc., which are not specifically limited here.

[0062] S120: Identify text data in the key information image using OCR technology, and establish an association relationship between the text data and the data class.

[0063] Optionally, OCR (Optical Character Recognition) is a technology that converts text in an image into editable text. A pre-trained OCR recognition model can be used to recognize text data in key information images.

[0064] Optionally, during the training process of the OCR recognition model, image data such as documents and receipts containing complex typesetting and blurred text can be used as a training set. During the training process, data enhancement techniques such as rotation, scaling, and adding noise can be used to improve the generalization ability of the model.

[0065] The establishment of an association relationship between text data and data classes may include:

[0066] Semantically encode text data and generate text vectors;

[0067] Match the text vector with a predefined key information template to obtain a similarity score; the key information template includes a description of the key information semantic features of the specified data class and regular expression matching rules;

[0068] When the similarity score between the text vector of the target text and the target key information template is higher than the preset score, the target text is determined as key information, and an association relationship is established between the target text and the corresponding data class according to the data class to which the target key information template belongs.

[0069] Optionally, a pre-trained language model based on deep learning can be used to semantically encode text data to generate a text vector. Each dimension value in the text vector represents the quantitative performance of the text in a specific semantic feature.

[0070] It is understandable that since the OCR model extracts text from key information images, there is a high possibility that non-key information may exist in the extracted text, such as information items that do not need to be filled in in documents, advertisements in web page screenshots, etc. Therefore, in order to improve the efficiency of data processing and the accuracy of the final evaluation results, it is necessary to extract key information from the extracted text data and only match the corresponding data class to the text data determined to be key information.

[0071] Optionally, the key information semantic feature description may refer to a formal description of the semantic connotation of the key information in a specified data class, which may be represented by a feature vector or a semantic label; the regular expression matching rule may refer to a text matching rule based on a string pattern, which quickly locates information in the text that conforms to a specific format through predefined character combinations.

[0072] Optionally, when the similarity score between the text vector and the target key information template is higher than a preset score, it may indicate that the text vector belongs to the data class to which the target key information template belongs.

[0073] The advantage of this setting is that it can reduce the interference of non-key data in the text data directly recognized by OCR. By adding the semantic feature description of key information in the key information template, it can determine whether the text belongs to the key information of a certain data class from the semantic level, avoiding the limitation of relying solely on surface text matching. By adding regular expression matching rules to the key information template, it can quickly filter the text from the grammatical structure level, supplement the deficiencies of semantic matching, and improve the accuracy of key information extraction.

[0074] After generating evaluation results of multiple evaluation indicators based on the association relationship between text data and data classes, the following steps may also be performed:

[0075] Conduct outlier drilldown analysis on the evaluation results of each evaluation indicator;

[0076] When an outlier is detected in the target evaluation result of the target evaluation indicator, an outlier analysis description and a solution strategy are generated for the outlier;

[0077] Generate an analysis file of the target evaluation results based on the target text data, outlier analysis description, and solution strategy used in the target evaluation indicator evaluation process, and establish an association relationship between the target evaluation result identifier and the analysis file;

[0078] Store the analysis file in cloud storage, generate an access link based on the storage location of the analysis file, and add a user signature to the access link.

[0079] Optionally, outlier drill-down analysis may refer to the process of tracing abnormal data in the evaluation results layer by layer to analyze its causes, impact scope, and associated factors.

[0080] Optionally, an outlier may refer to evaluation data that is different from an expected value. For example, if the score of a certain evaluation item is lower than a preset score value, the score is determined to be an outlier. This is only an example.

[0081] Optionally, the outlier analysis description may refer to a textual description of the nature, causes, and impacts of the outlier, which may be generated in combination with business logic and data features, and may include the outlier value and normal range, possible causes of the anomaly, etc. The solution strategy may refer to improvement measures or response plans proposed for the outlier.

[0082] Optionally, after a user signature is added to the access link, the accessing user must pass the user signature verification before accessing the analysis file, thereby ensuring the security of the analysis file.

[0083] The advantage of this setting is that an analysis file can be directly generated for the outliers based on the evaluation results. The analysis file clearly defines the causes and solutions of the outliers, provides credibility support for the outliers, and can fine-grainedly control data access rights to prevent data leakage.

[0084] S130: Generate evaluation results of multiple evaluation indicators based on the association relationship between the text data and the data class.

[0085] Optionally, the evaluation indicators may include data evaluation indicators, grade evaluation indicators, correlation evaluation indicators, basic information evaluation indicators, etc., without limiting the specific types of evaluation indicators.

[0086] Optionally, each evaluation indicator may pre-specify a data class for evaluation, and generate an evaluation result of the evaluation indicator by analyzing the text data under the specified data class.

[0087] Among them, based on the association relationship between text data and data classes, the evaluation results of multiple evaluation indicators are generated, which may include:

[0088] When the evaluation index is a data evaluation index, determining first text data for data calculation according to a calculation rule of the target data and an association relationship between the text data and the data class;

[0089] generating calculation results of target data based on the first text data, and arranging the calculation results of the target data according to time periods;

[0090] Based on the sorted calculation results, trend analysis charts and data descriptions are generated.

[0091] Optionally, the evaluation results of the data evaluation indicators need to be obtained by calculating relevant data, such as the pedestrian flow change index of the commercial area, the employee mobility index, etc., without limiting the specific data evaluation indicators.

[0092] Optionally, each data evaluation indicator pre-specifies a calculation rule for the data. The calculation rule may specify information such as the data type required for the calculation, the data recording time, etc. For example, the calculation rule for calculating the daily flow of people may be to add up the flow of people in each time period of the day, and the calculation result may be used as the daily flow of people.

[0093] Optionally, you can divide the calculation results and set the time range for statistics. Common time periods include day, week, month, quarter, year, etc. Calculation results can be sorted by time period to facilitate observation of data trends over time.

[0094] Optionally, a trend analysis chart may refer to a chart that graphically displays the trend of changes in calculation results over time, such as a line chart, a bar chart, an area chart, etc. Data description may refer to a textual explanation and description of the calculation results and trend analysis chart, including but not limited to the meaning of the data, the reasons for the changes, and the comparison with expectations.

[0095] The advantage of this setting is that by organizing the calculation results by time period in the evaluation results and generating charts, the data change trend can be intuitively displayed, the readability of the data can be improved, and by generating data descriptions, the business logic behind the data can be explained, lowering the decision-making threshold.

[0096] Among them, based on the association relationship between text data and data classes, the evaluation results of multiple evaluation indicators are generated, which may include:

[0097] When the evaluation indicator is a grade evaluation indicator, determining second text data for grade evaluation based on data factors required for grade evaluation and an association relationship between text data and data classes;

[0098] The second text data is input into a pre-trained evaluation model to obtain the evaluation score and evaluation grade output by the evaluation model, and a grade evaluation description is generated based on the evaluation score and evaluation grade; wherein the weight of each grade evaluation item is pre-set in the evaluation model, and the weight of each grade evaluation item is obtained based on a pre-constructed judgment matrix, which includes scores of multiple expert users on each grade evaluation item.

[0099] Optionally, grade evaluation indicators can be used to classify evaluation objects into different grades, such as excellent, good, qualified, and unqualified. They are usually based on a comprehensive assessment of multi-dimensional data factors rather than a single numerical calculation, such as supplier ratings, traffic ratings, etc.

[0100] Optionally, data factors may refer to the basic elements that constitute the grade assessment. For example, the data factors when evaluating suppliers may include delivery punctuality rate, product qualification rate, after-sales service response speed, etc. Each data factor corresponds to a specific data class.

[0101] Optionally, a judgment matrix can be constructed in advance, which includes scores given by multiple expert users on the importance of each level of evaluation items. After obtaining the importance scores, the importance scores can be judged for consistency to ensure the rationality of the scores. After passing the consistency judgment, the weights of the weights of the evaluation items of each level can be obtained by calculating the eigenvectors and maximum eigenvalues ​​of the judgment matrix.

[0102] Furthermore, based on the weights of the evaluation items at each level, the evaluation model is pre-trained. The evaluation model may be a support vector machine model, thereby obtaining penalty parameters and kernel function parameters.

[0103] Optionally, the evaluation score may refer to a quantitative score output by the model, such as 0-100 points, which comprehensively reflects the performance of the evaluation object under various data factors. The evaluation grade may refer to a qualitative grade divided according to the evaluation score, such as A, B, and C. The score intervals may be divided in advance, and different score intervals may correspond to different grades. No specific limitation is made here.

[0104] Optionally, after obtaining the assessment score and assessment grade, a grade assessment description may be generated. The grade assessment description may refer to a textual description of the assessment result, such as an explanation of the assessment score.

[0105] The advantage of this setting is that the judgment matrix can be used to integrate the experience and judgment of multiple experts, obtain weights that are closer to the actual evaluation criteria, reduce subjective bias, thereby improving the evaluation accuracy of the evaluation model and ensuring the rationality of the evaluation scores and evaluation results.

[0106] S140: Obtain a target assessment report template based on the third-party user attributes, and fill in the target assessment report template with the assessment results.

[0107] Optionally, third-party user attributes may refer to characteristic information of the evaluated object, such as industry type, enterprise size, business field, cooperation level, etc. Different evaluation report templates are pre-defined for different third-party user attributes. The evaluation report template includes a fixed chapter structure, indicator system and format specifications.

[0108] Optionally, after obtaining the evaluation results of each evaluation indicator, the evaluation results can be automatically mapped to corresponding positions in the report template according to the evaluation indicators, thereby filling in the target evaluation report template.

[0109] After filling the target assessment report template with the assessment results, the following steps may also be performed:

[0110] If there are outliers in the target evaluation results, an analysis file associated with the target evaluation results is determined, and an access link to the analysis file is added to the evaluation report.

[0111] The benefit of this setting is that by actively associating and embedding the access link of the analysis file, the analysis process of the outliers is directly presented to the report user, and at the same time a reference solution is provided to the user, thereby improving the user's decision-making time and improving business efficiency within the enterprise.

[0112] The technical solution of the embodiment of the present invention facilitates early data collection and later data storage by obtaining the key information image of the third-party user based on the identification of the third-party user. By using OCR technology, text data is identified in the key information image, and the association relationship between the text data and the data class is established. This can reduce the interference of non-key data in the text data directly identified by OCR, and facilitate the subsequent efficient acquisition of evaluation results. By generating evaluation results of multiple evaluation indicators based on the association relationship between the text data and the data class, obtaining the target evaluation report template according to the third-party user attributes, and using the evaluation results to fill in the target evaluation report template, multi-source data can be fully integrated to accurately evaluate the third-party user, and an evaluation report can be quickly generated. The comprehensiveness and accuracy of the information in the evaluation report can be guaranteed, and the problem that manual generation of evaluation reports is time-consuming and the accuracy of the report cannot be guaranteed.

[0113] Example 2

[0114] Figure 2 This is a flow chart of a method for generating an evaluation report provided by the second embodiment of the present invention. This embodiment specifically describes the method for generating an evaluation report based on the above embodiment. Figure 2 As shown, the method includes:

[0115] S210: Acquire a key information image of the third-party user according to the identifier of the third-party user.

[0116] S220: Recognize text data in the key information image using OCR technology.

[0117] S230: semantically encode the text data to generate a text vector.

[0118] After obtaining the key information image of the third-party user according to the identifier of the third-party user and recognizing text data in the key information image using OCR technology, the following steps may also be performed:

[0119] Generate a hash value for each key information image collected, and package the hash value of the key information image, data metadata, and collection number to generate a transaction;

[0120] The legitimacy of the transaction is verified based on the smart contract pre-deployed on the blockchain. If the transaction passes the verification, it is determined to be a legal transaction;

[0121] Generate an identifier for a legitimate transaction and record the legitimate transaction in the distributed ledger of the blockchain; the identifier of the legitimate transaction includes the timestamp of the legitimate transaction and the hash value of the previous block.

[0122] It is understandable that the key information image is the original data generated by the assessment report. Storing the key information image in the blockchain can enable timely data tracing when problems arise later, providing strong evidence of the validity of the assessment report.

[0123] Optionally, the data metadata may include information such as data source and acquisition time, and the acquisition number may refer to a unique number generated when the key information image is acquired.

[0124] Optionally, a smart contract may refer to an automatically executing program deployed on a blockchain that verifies and executes transactions based on preset rules, and a distributed ledger may refer to a shared ledger maintained by all nodes in a blockchain network that stores all legal transaction records, with each node holding a complete copy.

[0125] Optionally, the smart contract can check whether the transaction data metadata is complete and compliant, whether the collection time is within a reasonable range, and whether the data source is a trusted channel pre-set by the enterprise, so as to avoid future time or obviously erroneous time records and ensure that the data is legal and compliant. If the smart contract determines that the transaction is illegal, it will refuse to enter the subsequent process.

[0126] Furthermore, smart contracts can also verify hash values. Smart contracts can use the same hash algorithm as when generating hash values ​​to recalculate the hash value of the data metadata contained in the transaction and compare it with the hash value of the transaction itself. Due to the characteristics of the hash function, even if there are slight changes in the data metadata, the recalculated hash value will be different from the original hash value. If the comparison results are inconsistent, it means that the data may have been tampered with during the transmission or packaging process. The smart contract will mark the transaction as illegal. Only when the recalculated hash value completely matches the hash value in the transaction, it means that the data is intact and has not been tampered with.

[0127] Optionally, by adding the timestamp of the legal transaction and the hash value of the previous block to the identifier of the legal transaction, it can be ensured that the current transaction is closely linked to the previous block, ensuring the continuity and traceability of the data.

[0128] The advantage of this setting is that by adding hash values ​​and using hash values ​​for verification, it can be ensured that the data has not been tampered with throughout the entire process from collection to chain upload. By adding the timestamp of the legal transaction and the hash value of the previous block in the identifier of the legal transaction, it can be ensured that the current transaction is closely linked to the previous block, ensuring the continuity and traceability of the data. By recording legal transactions in the distributed ledger, the distributed ledger can be maintained by all nodes in the network. Even if a single point is offline, it can still be guaranteed that data will not be lost. Verification through smart contracts can avoid future time or obviously erroneous time records, ensuring the legality and compliance of the data.

[0129] S240: Match the text vector with a predefined key information template to obtain a similarity score.

[0130] The key information template includes a description of the key information semantic features of the specified data class and regular expression matching rules.

[0131] S250. When the similarity score between the text vector of the target text and the target key information template is higher than a preset score, the target text is determined as key information, and an association relationship is established between the target text and the corresponding data class according to the data class to which the target key information template belongs.

[0132] S260: Generate evaluation results of multiple evaluation indicators based on the association relationship between the text data and the data class.

[0133] S270: Perform outlier drilldown analysis on the evaluation results of each evaluation indicator.

[0134] S280: When an outlier is detected in the target evaluation result of the target evaluation indicator, an outlier analysis description and a solution strategy are generated for the outlier.

[0135] S290. Generate an analysis file of the target evaluation result based on the target text data, outlier analysis description, and solution strategy used in the target evaluation indicator evaluation process, and establish an association relationship between the identifier of the target evaluation result and the analysis file.

[0136] S2100: Store the analysis file in cloud storage, generate an access link according to the storage location of the analysis file, and add a user signature to the access link.

[0137] S2110. Obtain a target assessment report template based on third-party user attributes, and fill in the target assessment report template using the assessment results.

[0138] S2120. If there are outliers in the target evaluation result, determine the analysis file associated with the target evaluation result, and add the access link of the analysis file to the evaluation report.

[0139] The technical solution of the embodiment of the present invention is to obtain the key information image of the third-party user according to the identification of the third-party user, so as to facilitate the early data collection and the later data evidence storage. By using the OCR technology, the text data is identified in the key information image, and the relationship between the text data and the data class is established. This can reduce the interference of non-key data in the text data directly identified by OCR, and facilitate the subsequent efficient acquisition of evaluation results. By generating the evaluation results of multiple evaluation indicators according to the relationship between the text data and the data class, obtaining the target evaluation report template according to the third-party user attributes, and using the evaluation results to fill in the target evaluation report template, it is possible to fully integrate multi-source data for third-party users. It can conduct accurate assessments on users and quickly generate assessment reports, ensuring the comprehensiveness and accuracy of the information in the assessment reports. It solves the problem that manual generation of assessment reports takes a long time and the accuracy of the reports cannot be guaranteed. In addition, by generating analysis files and adding access links to target assessment results with outliers, the causes and solutions of the outliers can be clarified, credibility support can be provided for the outliers, and data access rights can be controlled in a fine-grained manner to prevent data leakage. By actively associating and embedding access links to analysis files, the analysis process of outliers is directly presented to report users, and at the same time, users are provided with solutions for reference, thereby improving users' decision-making time and improving business efficiency within the enterprise.

[0140] Example 3

[0141] Figure 3 This is a schematic diagram of the structure of an evaluation report generating device provided by the third embodiment of the present invention. Figure 3As shown, the device includes: a key information image acquisition module 310, a text data extraction module 320, an evaluation result generation module 330 and a template filling module 340.

[0142] The key information image acquisition module 310 is used to obtain the key information image of the third-party user according to the identifier of the third-party user.

[0143] The text data extraction module 320 is used to identify text data in key information images through OCR technology and establish an association relationship between the text data and data classes.

[0144] The evaluation result generation module 330 is used to generate evaluation results of multiple evaluation indicators based on the association relationship between text data and data classes.

[0145] The template filling module 340 is used to obtain a target evaluation report template according to the third-party user attributes, and fill the target evaluation report template with the evaluation result.

[0146] The technical solution of the embodiment of the present invention facilitates early data collection and later data storage by obtaining the key information image of the third-party user based on the identification of the third-party user. By using OCR technology, text data is identified in the key information image, and the association relationship between the text data and the data class is established. This can reduce the interference of non-key data in the text data directly identified by OCR, and facilitate the subsequent efficient acquisition of evaluation results. By generating evaluation results of multiple evaluation indicators based on the association relationship between the text data and the data class, obtaining the target evaluation report template according to the third-party user attributes, and using the evaluation results to fill in the target evaluation report template, multi-source data can be fully integrated to accurately evaluate the third-party user, and an evaluation report can be quickly generated. The comprehensiveness and accuracy of the information in the evaluation report can be guaranteed, and the problem that manual generation of evaluation reports is time-consuming and the accuracy of the report cannot be guaranteed.

[0147] Based on the above embodiments, the text data extraction module 320 can be specifically used to:

[0148] Semantically encode text data and generate text vectors;

[0149] Match the text vector with a predefined key information template to obtain a similarity score; the key information template includes a description of the key information semantic features of the specified data class and regular expression matching rules;

[0150] When the similarity score between the text vector of the target text and the target key information template is higher than the preset score, the target text is determined as key information, and an association relationship is established between the target text and the corresponding data class according to the data class to which the target key information template belongs.

[0151] Based on the above embodiments, the evaluation result generation module 330 can be specifically used to:

[0152] When the evaluation index is a data evaluation index, determining first text data for data calculation according to a calculation rule of the target data and an association relationship between the text data and the data class;

[0153] generating calculation results of target data based on the first text data, and arranging the calculation results of the target data according to time periods;

[0154] Based on the sorted calculation results, trend analysis charts and data descriptions are generated.

[0155] Based on the above embodiments, the evaluation result generation module 330 can be specifically used to:

[0156] When the evaluation indicator is a grade evaluation indicator, determining second text data for grade evaluation based on data factors required for grade evaluation and an association relationship between text data and data classes;

[0157] The second text data is input into a pre-trained evaluation model to obtain the evaluation score and evaluation grade output by the evaluation model, and a grade evaluation description is generated based on the evaluation score and evaluation grade; wherein the weight of each grade evaluation item is pre-set in the evaluation model, and the weight of each grade evaluation item is obtained based on a pre-constructed judgment matrix, which includes scores of multiple expert users on each grade evaluation item.

[0158] Based on the above embodiments, an analysis file generation module may be further included to:

[0159] Conduct outlier drilldown analysis on the evaluation results of each evaluation indicator;

[0160] When an outlier is detected in the target evaluation result of the target evaluation indicator, an outlier analysis description and a solution strategy are generated for the outlier;

[0161] Generate an analysis file of the target evaluation results based on the target text data, outlier analysis description, and solution strategy used in the target evaluation indicator evaluation process, and establish an association relationship between the target evaluation result identifier and the analysis file;

[0162] Store the analysis file in cloud storage, generate an access link based on the storage location of the analysis file, and add a user signature to the access link.

[0163] Based on the above embodiments, an access link adding module may be further included, which is used to:

[0164] If there are outliers in the target evaluation results, an analysis file associated with the target evaluation results is determined, and an access link to the analysis file is added to the evaluation report.

[0165] Based on the above embodiments, a blockchain storage module may also be included for:

[0166] Generate a hash value for each key information image collected, and package the hash value of the key information image, data metadata, and collection number to generate a transaction;

[0167] The legitimacy of the transaction is verified based on the smart contract pre-deployed on the blockchain. If the transaction passes the verification, it is determined to be a legal transaction;

[0168] Generate an identifier for a legitimate transaction and record the legitimate transaction in the distributed ledger of the blockchain; the identifier of the legitimate transaction includes the timestamp of the legitimate transaction and the hash value of the previous block.

[0169] The evaluation report generating device provided in the embodiment of the present invention can execute the evaluation report generating method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0170] Example 4

[0171] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0172] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0173] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0174] The processor 11 can be various general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as the evaluation report generation method described in an embodiment of the present invention. That is:

[0175] Obtaining a key information image of the third-party user based on the third-party user's identifier;

[0176] Use optical character recognition (OCR) technology to identify text data in key information images and establish associations between text data and data classes;

[0177] Generate evaluation results of multiple evaluation indicators based on the association relationship between text data and data classes;

[0178] According to the third-party user attributes, a target assessment report template is obtained, and the target assessment report template is filled with the assessment results.

[0179] In some embodiments, the assessment report generation method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the assessment report generation method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the assessment report generation method by any other appropriate means (e.g., by means of firmware).

[0180] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0181] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0182] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0183] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0184] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0185] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0186] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0187] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for generating an evaluation report, characterized in that: include: Obtaining a key information image of the third-party user based on the third-party user's identifier; Use optical character recognition (OCR) technology to identify text data in key information images and establish associations between text data and data classes; Generate evaluation results of multiple evaluation indicators based on the association relationship between text data and data classes; According to the third-party user attributes, a target assessment report template is obtained, and the target assessment report template is filled with the assessment results.

2. The method according to claim 1, characterized in that Establish the relationship between text data and data classes, including: Semantically encode text data and generate text vectors; Match the text vector with a predefined key information template to obtain a similarity score; the key information template includes a description of the key information semantic features of the specified data class and regular expression matching rules; When the similarity score between the text vector of the target text and the target key information template is higher than the preset score, the target text is determined as key information, and an association relationship is established between the target text and the corresponding data class according to the data class to which the target key information template belongs.

3. The method according to claim 1, characterized in that Based on the relationship between text data and data classes, the evaluation results of multiple evaluation indicators are generated, including: When the evaluation index is a data evaluation index, determining first text data for data calculation according to a calculation rule of the target data and an association relationship between the text data and the data class; generating calculation results of target data based on the first text data, and arranging the calculation results of the target data according to time periods; Based on the sorted calculation results, trend analysis charts and data descriptions are generated.

4. The method according to claim 1, wherein Based on the relationship between text data and data classes, the evaluation results of multiple evaluation indicators are generated, including: When the evaluation indicator is a grade evaluation indicator, determining second text data for grade evaluation based on data factors required for grade evaluation and an association relationship between text data and data classes; The second text data is input into a pre-trained evaluation model to obtain the evaluation score and evaluation grade output by the evaluation model, and a grade evaluation description is generated based on the evaluation score and evaluation grade; wherein the weight of each grade evaluation item is pre-set in the evaluation model, and the weight of each grade evaluation item is obtained based on a pre-constructed judgment matrix, which includes scores of multiple expert users on each grade evaluation item.

5. The method according to claim 1, wherein After generating the evaluation results of multiple evaluation indicators based on the association between text data and data classes, it also includes: Conduct outlier drilldown analysis on the evaluation results of each evaluation indicator; When an outlier is detected in the target evaluation result of the target evaluation indicator, an outlier analysis description and a solution strategy are generated for the outlier; Generate an analysis file of the target evaluation results based on the target text data, outlier analysis description, and solution strategy used in the target evaluation indicator evaluation process, and establish an association relationship between the target evaluation result identifier and the analysis file; Store the analysis file in cloud storage, generate an access link based on the storage location of the analysis file, and add a user signature to the access link.

6. The method according to claim 5, characterized in that After filling the target assessment report template with the assessment results, the following steps are further included: If there are outliers in the target evaluation results, an analysis file associated with the target evaluation results is determined, and an access link to the analysis file is added to the evaluation report.

7. The method according to claim 1, characterized in that After obtaining the key information image of the third-party user according to the identifier of the third-party user and recognizing text data in the key information image using OCR technology, the method further includes: Generate a hash value for each key information image collected, and package the hash value of the key information image, data metadata, and collection number to generate a transaction; The legitimacy of the transaction is verified based on the smart contract pre-deployed on the blockchain. If the transaction passes the verification, it is determined to be a legal transaction; Generate an identifier for a legitimate transaction and record the legitimate transaction in the distributed ledger of the blockchain; the identifier of the legitimate transaction includes the timestamp of the legitimate transaction and the hash value of the previous block.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to execute the evaluation report generating method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the evaluation report generation method according to any one of claims 1 to 7 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the method for generating an assessment report according to any one of claims 1 to 7.

Images