Product stage authentication method and device based on mobile collaborative electronic signature

Abstract

The invention discloses a product stage authentication method and device based on a mobile collaborative electronic signature, and relates to the technical field of security certification, and the method comprises the steps: generating a first feature vector representing the core content of product authentication application data; obtaining a second feature vector representing the index text of the target product; the index text is generated based on a first feature vector of core content of each finished product authentication application data of the target product and a plurality of research and development stage tags corresponding to the target product; the research and development stage label corresponding to the target product is determined according to the category of the target product; inputting the first feature vector and the second feature vector into a trained neural network model to obtain an output result representing whether the core content of the product authentication application data is added into the index text; and if the output result is yes, generating a stage authentication electronic seal of the target product. According to the invention, the security, timeliness, legality and convenience of submission of the authentication application data are ensured.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a product phased authentication method and device based on mobile collaborative electronic signature. Background Art

[0002] With the popularization of mobile Internet and the development of informatization of product certification business, various online product certification application materials, as the foundation and core of product certification business, are increasingly used in various categories of product certification activities.

[0003] In the process of realizing the present invention, the inventor discovered that certain products must undergo phased product certification due to their particularity, such as long R&D cycle or belonging to a product series. In this certification process, it is necessary to have an in-depth and full understanding of the certification application materials for this time, and it is also necessary to retrieve the last certification application materials to determine whether the product meets the phased progress and thus grant certification. Since it is necessary to carefully analyze the current information and review the past information, a lot of time is consumed, and the entire certification process is obviously untimely. In addition, the entire process requires extremely high professionalism from the certification personnel in order to determine whether the phased progress of the product meets the certification standards. This high requirement makes the number of qualified certification personnel relatively small, further affecting the efficiency of certification. In addition, the traditional electronic signature method has poor security. Although it guarantees the legitimacy and anti-repudiation of the application materials to a certain extent, it does not guarantee the legal identity of the person submitting the certification application materials. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present invention provide a product phased authentication method and device based on mobile collaborative electronic signature, which can intelligently determine whether the product meets the phased progress according to the authentication application materials and thus grant authentication, thereby improving the authentication efficiency and ensuring the security, timeliness, legality and convenience of submitting the authentication application materials.

[0005] The embodiment of the present invention provides a product phased authentication method based on mobile collaborative electronic signature, including: Receive product certification application materials of a target product, and generate a first feature vector representing the core content of the product certification application materials; obtain a second feature vector representing an index text of the target product; wherein the index text is generated based on the first feature vector of the core content of each completed product certification application material of the target product and a plurality of R&D stage labels corresponding to the target product; the R&D stage label corresponding to the target product is determined according to the category of the target product; input the first feature vector and the second feature vector into a pre-trained neural network model to obtain an output result; the output result is used to represent whether the core content of the product certification application materials is added to the index text; if the output result is yes, generate a mobile collaborative electronic signature for the phased certification of the target product.

[0006] The embodiment of the present invention further provides a product phased authentication device based on mobile collaborative electronic signature, comprising: The first generation module is used to receive product certification application materials of a target product and generate a first feature vector representing the core content of the product certification application materials; the acquisition module is used to acquire a second feature vector representing an index text of the target product; wherein the index text is generated based on the first feature vector of the core content of each completed product certification application material of the target product and a plurality of R&D stage labels corresponding to the target product; the R&D stage label corresponding to the target product is determined according to the category of the target product; the output module is used to input the first feature vector and the second feature vector into a pre-trained neural network model to obtain an output result; the output result is used to represent whether the core content of the product certification application materials is added to the index text; the second generation module is used to generate a mobile collaborative electronic signature for the phased certification of the target product if the output result is yes.

[0007] An embodiment of the present invention further provides an electronic device, the electronic device comprising: One or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the product phased authentication method based on mobile collaborative electronic signature as described above.

[0008] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the product phased authentication method based on mobile collaborative electronic signature as described above is implemented.

[0009] An embodiment of the present invention further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the method for phased product authentication based on mobile collaborative electronic signature as described above is implemented.

[0010] The product phased authentication method and device based on mobile collaborative electronic signature provided by the embodiments of the present invention have at least the following advantages compared with the prior art: the present invention can intelligently determine whether the product meets the phased progress based on the authentication application materials and thus grant authentication, thereby improving the authentication efficiency and ensuring the security, timeliness, legality and convenience of submitting the authentication application materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0012] Figure 1 A flowchart of a product phased authentication method based on a mobile collaborative electronic signature provided for an embodiment of the present application; Figure 2 A flowchart of a method for generating a mobile collaborative electronic signature for phased authentication of a target product provided by an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application; Figure 4 A schematic diagram of the structure of a product phased authentication device based on a mobile collaborative electronic signature provided for one embodiment of the present application. DETAILED DESCRIPTION

[0013] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0014] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0015] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] refer to Figure 1 As shown, an embodiment of the present invention provides a product phased authentication method based on mobile collaborative electronic signature, which is executed on a product authentication application material submission system server in the form of a computer program, and includes the following steps: Step S101, receiving product certification application materials of a target product, and generating a first feature vector representing the core content of the product certification application materials.

[0019] In this step, the product certification application materials may include text or images.

[0020] For the text, firstly, the text segmentation algorithm in natural language processing technology is used to segment the text of the application materials into paragraphs, sentences or chapters. For each segmented unit, it is marked according to the key information category to which it belongs, such as "basic product information", "technical parameters", "experimental results", etc. Secondly, for the key information of each segmented unit, the word frequency statistics and keyword extraction are performed. Specifically, the word frequency-inverse document frequency (TF-IDF) algorithm can be used to calculate the importance weight of each word. TF-IDF can highlight the words that frequently appear in the product certification application materials of the target product and relatively rarely appear in the certification application materials of similar products. These words often have high discrimination and representativeness. Based on the TF-IDF results, the first several words with higher weights are selected as the keywords of the key information. For example, for the basic information of the product, the key materials related to the product ingredients and the key numbers in the model may be extracted as keywords. Finally, an initial vector is created for each key information, and the dimension of the initial vector is equal to the number of keywords extracted from the key information. Each dimension corresponds to a keyword, and its value can be initialized according to the importance weight of the keyword (such as the TF-IDF value). The vectors of all key information are spliced ​​in a predetermined order (for example, in the order of basic product information, technical parameters, production process flow, experimental results, etc.) to form a long vector. This long vector is the first feature vector that represents the core content of the product certification application materials.

[0021] As an optional implementation manner of an embodiment of the present invention, the generation of a first feature vector representing the core content of the product certification application materials includes: segmenting the product certification application materials to obtain at least one text segment; for each of the text segments, obtaining a previous text segment corresponding to the text segment, and a summary vector of the previous text segment, wherein the previous text segment is all text segments before the text segment in the product certification application materials, and concatenating the summary vector of the previous text segment and the feature vector of the text segment to obtain a summary vector of the text segment; and generating a first feature vector representing the core content of the product certification application materials based on the summary vectors corresponding to each of the text segments.

[0022] In this scheme, each text segment generates both a feature vector of the text segment and a summary vector of the text segment. The summary vector of the text segment is obtained by understanding and summarizing the text segment and the context of the text segment. In other words, each word in the defined text segment is understood through the context, so that the key information of the text segment can be more accurately extracted.

[0023] Specifically, the sentence segmentation algorithm in natural language processing technology is used to segment the product certification application materials to ensure that each text segment is relatively independent and complete in semantics. Preliminary segmentation can be performed according to rules such as punctuation and paragraph separation. For each text segment, after determining its previous text segment, the previous text segment is input into the pre-trained generative model (such as GPT series, BERT, etc.) in sequence to obtain the vector representation of the specific layer output by the generative model as the initial encoding result. Then, the initial encoding result is further processed using a text summary algorithm (such as TextRank, Transformer-based summary model, etc.) to extract key information and generate a summary text. Then, the summary text is input into the generative model again to obtain its corresponding vector representation as the summary vector of the previous text segment.

[0024] Furthermore, the summary vector of the above text segment and the feature vector of the text segment are concatenated. Before concatenation, the two vectors can be normalized to ensure that they have similarity in numerical range. For example, the min-max normalization method is used to map the values ​​of the vectors to the interval [0, 1]. The concatenated vectors can be further fused through a fully connected neural network to obtain the summary vector of the text segment.

[0025] Finally, based on the summary vectors corresponding to each text segment, clustering algorithms (such as K-Means clustering, hierarchical clustering, etc.) can be used to group these vectors. Each cluster represents a topic or feature type. By analyzing the distribution of cluster centers and vectors within clusters, key feature information can be extracted. The center vectors of each cluster are weighted and summed to obtain the first feature vector that represents the core content of the product certification application materials. The weight can be determined based on factors such as the size and importance of the cluster. For example, a higher weight can be given to a cluster containing more text segments.

[0026] For pictures, first perform preprocessing operations such as denoising and enhancement to improve image quality. And adjust the image size so that all pictures have a uniform size for subsequent processing. Secondly, based on traditional image processing methods, such as color histograms and texture features, the features of the picture can be extracted, and the extracted features can be combined into the first feature vector to represent the image. Among them, the color histogram can describe the color distribution of the picture, and the texture features can reflect the texture structure of the picture. In addition, deep learning models such as convolutional neural networks (CNNs) can also be used to extract the features of the picture, and the output of the last fully connected layer is used as the first feature vector of the picture.

[0027] Furthermore, if the product certification application materials may include text and images, it is necessary to concatenate the first feature vector of the text and the first feature vector of the image in a certain order to obtain a joint first feature vector.

[0028] The inventors discovered during the process of implementing the present invention that the appearance of pictures generally assists in understanding text. Therefore, in order to be able to understand pictures more accurately, as an optional implementation method of an embodiment of the present invention, the product certification application materials include pictures, and the method further includes: for each of the pictures, inputting the picture into a generative model to obtain a description text of the picture; in the product certification application materials, determining a target text segment related to the picture, and integrating the description text with the target text segment.

[0029] Specifically, the image types of images in the product certification application materials include data types that represent experimental effects, product form types that represent the basic information of the target product, and structural types that represent the production process flow, etc. Different image types correspond to different prompt information, which is used to represent the key information dimensions that need to be described in the image of this type. The dimensions of the key information match the image type (for example, the dimension of the data type is data analysis, the dimension of the product form type is the morphological description, and the dimension of the structure type is the structure and connection description, etc.). The image and the prompt information corresponding to the image type of the image are input into the generative model together to obtain the description text. This description text can be a sentence or a short paragraph, describing the main content and features of the key information dimensions that need to be described in the image. The generative model can use pre-trained visual language models, such as CLIP (Contrastive Language–Image Pretraining) or DALLE 2. These models are trained on a large amount of image and text pair data, and can combine the prompt information to understand the image content well and generate corresponding description text. A multimodal model based on the Transformer architecture can also be used to achieve the generation of image to description text through joint learning of image features and text features.

[0030] Furthermore, based on the position of the image in the product certification application materials, several text fragments close to the image position are determined, and the bag-of-words model, TF-IDF and other methods are used to extract the keywords and feature vectors of each text fragment. The correlation between the descriptive text and each text fragment is calculated by calculating indicators such as cosine similarity and Jaccard similarity between text vectors. Text fragments whose correlation exceeds a preset threshold are determined as target text fragments related to the image.

[0031] A simple concatenation method can be used to directly connect the image description text and the target text segment. For example, the image description text can be inserted at the beginning or end of the target text segment and distinguished by a specific delimiter. More complex fusion methods can also be used, such as fusion based on the attention mechanism. By training an attention model, the model automatically learns the importance weights between the image description text and the target text segment, and then performs weighted fusion.

[0032] Optionally, this solution can also calculate the similarity between pictures first. For pictures with high similarity, picture groups representing the same key information can be identified (such as pictures of product forms at different magnifications, data analysis of different dimensions under the same indicator, etc.), and the descriptive texts of the picture groups can be aggregated into descriptive text groups to uniformly determine and integrate target text fragments.

[0033] As an optional implementation scheme of an embodiment of the present invention, if the picture includes text, the picture is input into a generative model to obtain a description text of the picture, including: recognizing the picture to obtain a text recognition result; determining the image quality of the picture based on an image feature vector of the picture, wherein the image quality is used to characterize the clarity of the picture; inputting the text recognition result, the image feature vector and the image quality score into a pre-trained generative model to obtain a description text of the picture; the image quality score is used to determine the participation weight of the text recognition result when the generative model understands the picture.

[0034] The higher the image quality score, the higher the clarity of the text in the picture, and the lower the image quality score, the lower the clarity of the text in the picture. The biggest feature of the generative model is its ability to understand and generate content, that is, it can predict the text in the picture based on the image feature vector. In other words, on the basis of recognizing the picture according to the optical character recognition method to obtain the text recognition result, the generative model can correct the text recognition result in combination with the understanding of the picture to ensure the accuracy of the text recognition result, and then obtain the description text of the picture based on the prompt information, the image feature vector and the corrected text recognition result.

[0035] In this solution, a mapping relationship table between image clarity and image quality score can be pre-set. After obtaining the image quality score corresponding to the image clarity, the model participation weight of the generative model in the process of text content recognition of the image is adjusted according to the image quality score, so that the degree of correction of the preliminary text recognition results by the generative model in text content recognition varies with the image quality score. For example, if the clarity of the text in the image is high, the text in the image can be recognized only by the optical character recognition method, that is, the generative model does not need to correct the text recognition results, and directly obtains the description text of the image based on the prompt information, image feature vector and text recognition results.

[0036] Before implementing this solution, collect a batch of pictures with known clarity as training data, extract their image feature vectors, and annotate the corresponding clarity levels (such as high clarity, medium clarity, low clarity, etc.). Use machine learning algorithms such as support vector machines (SVM), random forests, neural networks, etc. to train the clarity assessment model. Use the image feature vector of the picture as input and the clarity level as output for supervised learning. Optionally, the image feature vector of the picture can be obtained through deep learning methods (using pre-trained convolutional neural networks such as VGG, ResNet, etc.).

[0037] Step S102, obtaining a second feature vector of an index text representing the target product; wherein the index text is generated based on a first feature vector of the core content of each product certification application material completed by the target product and a plurality of R&D stage labels corresponding to the target product; and the R&D stage label corresponding to the target product is determined according to the category of the target product.

[0038] The research and development of target products usually go through multiple different stages. For example, the research and development stages of chemical products include the formulation research stage, reaction condition research stage, equipment process research stage, etc.; the research and development stages of medical device products include the material research and development stage, equipment structure research and development stage, safety research stage, effectiveness testing stage, etc. The research and development information of different categories of products is counted in advance, and the research and development stages of each category of products are obtained by statistical clustering, so as to determine the research and development stage labels of each category of products.

[0039] Here, the index text of the target product includes the first R&D stage labels of multiple R&D stages of the target product that have completed certification, and the second R&D stage labels of the R&D stages that have not completed certification; the index file also includes the first feature vector of the core content of the product certification application materials corresponding to each first R&D stage label.

[0040] In this step, the first feature vector is converted into a text description and then concatenated with the R&D stage label. For example, the key feature words in the vector can be extracted to form a descriptive text, and then the R&D stage label is added and integrated with the corresponding R&D stage label. The first feature vector and the R&D stage label are structured using a specific format or template for subsequent processing. For example, the JSON format can be used to store the feature vector and the label as different fields. Based on this, the concatenated text of each R&D stage is obtained, and the concatenated text of each R&D stage is input into a deep learning model, such as a language model of the Transformer architecture (BERT, GPT, etc.), and the index text is encoded to obtain the second feature vector.

[0041] As an optional implementation of the embodiment of the present invention, the index text is generated based on the first feature vector of the core content of each product certification application material completed by the target product and multiple R&D stage labels corresponding to the target product, specifically including: Step S1021, setting a plurality of nodes of the index text according to each of the research and development stage labels.

[0042] Here, the R&D stage label includes multiple levels. For example, the first-level R&D stage label includes the formula research stage, the reaction condition research stage, and the equipment process research stage. The second-level R&D stage label is a sub-label of the first-level R&D stage label. For example, the formula research stage label includes sub-labels such as the new ingredient research label and the new ratio research label. Specifically, the level of the label can be determined according to the granularity of the phased certification. For example, if the granularity of the certification is coarse, only the node of the index text is set for the first-level R&D stage label, that is, one node is set for each R&D stage label. For example, if the granularity of the certification is fine, two layers of nodes can be set for the first-level R&D stage label and the second-level R&D stage label.

[0043] Step S1022, determining the explanation text of each of the nodes and generating a third feature vector of the explanation text, wherein the explanation text is used to characterize the key features of the target product required by each node.

[0044] In this step, the method for generating the third eigenvector is as described above and will not be repeated here. The explanatory text is used to characterize the key features of each dimension that the target product needs to achieve in the R&D stage corresponding to this node. For example, the corresponding dimensions in the formula research stage include the innovation, feasibility and safety of the formula. The key features of the innovation dimension include new chemical structures, reaction pathways or performance characteristics. The key features of the feasibility dimension include the feasibility of chemical reactions, the stability of products and preliminary tests of expected performance. The key features of the safety dimension include the toxicity of raw materials, potential hazards in the reaction process and specific values ​​of the safety of the final product.

[0045] As some optional implementation modes of the present invention, the determining of the interpretation text of each of the nodes includes: Determine search keywords and at least one genre search intent based on the R&D stage label corresponding to each node; search and obtain multiple multimedia information corresponding to the genre search intent based on the search keywords; perform multimodal understanding on the multiple multimedia information to determine the explanation text of each of the nodes.

[0046] Here, it is necessary to summarize and determine the required features to be achieved in each R&D stage by searching for product information of the same type as the target product corresponding to each R&D stage. Specifically, the R&D stage label corresponding to each node, as well as the synonyms and near synonyms of the R&D stage label, are used as search keywords, and the key features of the R&D stage are determined based on the R&D stage label through which or which genres of product information are needed to summarize and determine. For example, in the safety dimension of the formula research stage, product information in the picture genre is required to determine the state of the reaction process. Therefore, after determining the search keywords and at least one genre search intent, multiple multimedia information is searched. Multimodal fusion algorithms, such as fusion based on attention mechanism, fusion based on feature splicing, etc., can be used to fuse information of different modalities to generate explanatory text.

[0047] Step S1023, calculating the similarity between the third feature vector of each explanation text and the first feature vector of the core content of each completed product certification application document, and obtaining the target product certification application document under each node.

[0048] Specifically, for each explanation text, the bag-of-words model, TF-IDF or more advanced text vector representation methods in natural language processing, such as Word2Vec, GloVe or language models based on deep learning (such as BERT, GPT, etc.) are used to extract feature vectors as the third feature vectors. And through methods such as cosine similarity, Euclidean distance, Pearson correlation coefficient, etc., the similarity between the third feature vector of each explanation text and the first feature vector of each completed product certification application document is calculated respectively, and for each node, it is sorted according to the calculated similarity value. The product certification application document with the highest similarity can be selected as the product certification application document for the target product under this node.

[0049] Step S1024: for each of the nodes, generate the index text according to the core content of the target product certification application materials under the node.

[0050] Specifically, the first feature vector of the core content of the target product certification material has been generated according to the above steps. Therefore, the index text is generated based on the R&D stage label of each node, the third feature vector of the explanatory text, and the first feature vector of the core content of the target product certification material.

[0051] Step S103, inputting the first feature vector and the second feature vector into a pre-trained neural network model to obtain an output result; the output result is used to indicate whether the core content of the product certification application materials is added to the index text.

[0052] In this step, a neural network model suitable for processing vector input can be selected according to the type of target product, such as a multi-layer perceptron (MLP), a convolutional neural network (CNN) combined with a fully connected layer, or a recurrent neural network (RNN) variant such as a long short-term memory network (LSTM), a gated recurrent unit (GRU), etc. If the first feature vector and the second feature vector of the input contain sequence information or complex relationships, RNN and its variants are more suitable as neural network models. Specifically, the samples in the training set include the first feature vector of the core content of the product certification application materials, the second feature vector of the index text, and the probability that the product certification application materials correspond to the target node in the index text. The probability is calculated based on the similarity between the first feature vector of the core content of the product certification application materials and the third feature vector of the explanation text corresponding to each node of the index text.

[0053] The input layer of the neural network model receives the concatenation of the first eigenvector and the second eigenvector, and can connect the two vectors together through a simple concatenate operation. The middle hidden layer can use activation functions such as ReLU and tanh to increase the nonlinear expression ability of the model. The output layer uses the sigmoid function to map the output value to the [0,1] interval, indicating the probability of adding the core content of the product certification application materials to the index text. Whether to add the core content of the application materials to the index text is determined based on the output result. That is, if the output result is close to 1, it means it should be added; if it is close to 0, it means it should not be added.

[0054] As an optional implementation of the embodiment of the present invention, the output result is used to indicate whether the core content of the product certification application materials is added to the index text, including: The output result is used to represent that the core content of the product certification application materials corresponds to the first target node of the index text, and there is no corresponding target product certification application material under the first target node; or, The output result is used to represent that the core content of the product certification application materials corresponds to the second target node of the index text, and the corresponding target product certification application materials exist under the second target node. The core content of the product certification application materials is used to update the second target node.

[0055] If the output result is yes, execute step S104.

[0056] Here, the output result close to 1 includes two possibilities. The first possibility is that the similarity between the first feature vector of the core content of the product certification application material and the third feature vector of the interpretation text of the first target node is greater than the preset threshold, and there is no corresponding target product certification application material under the first target node; the second possibility is that the similarity between the first feature vector of the core content of the product certification application material and the third feature vector of the interpretation text of the second target node is greater than the preset threshold, but there is a corresponding target product certification application material under the second target node. By calculating the similarity between the first feature vector of the core content of the target product certification application material and the first feature vector of the core content of the product certification application material of the target product, it is determined that the similarity between the two is less than the preset threshold, indicating that the product certification application material of the target product under the second target node has been substantially updated (in this case, the second target node needs to be certified multiple times). Both of the above situations indicate that the core content of the product certification application material needs to be added to the index text.

[0057] Step S104, generating a mobile collaborative electronic signature for phased authentication of the target product.

[0058] Specifically, through the certification application materials of the target product, it can be determined that the target product meets the phased progress and is thus certified. The certification method is to generate a mobile collaborative electronic signature for the phased certification of the target product.

[0059] The commonly used method for submitting traditional product certification application materials is: the person in charge of the certification applicant first determines the final content of the certification application materials through electronic data interaction or real-time communication tools, and then uses physical means or traditional electronic signature methods to complete the signature, and finally submits it to the certification body by mailing paper materials or electronic data interaction. This method is cumbersome to operate. Since the identity of the person in charge of the certification applicant is not authenticated by real name and the enterprise is not authorized during the confirmation and submission of the certification application materials, and the product certification application is not encrypted during the submission process, it is easy to be tampered with, posing a threat to the business secrets and transaction security of the certification applicant, and there is a lack of security control over the management of the submitted certification application materials. Although the traditional electronic signature method can guarantee the legitimacy and non-repudiation of the certification application materials, it is not timely for the person in charge of the certification application to submit the certification application materials.

[0060] In order to solve the technical problem that the legal identity of the product certification applicant's agent in the product certification application information submission system is not timely, as some optional implementation methods of the present invention, such as Figure 2 As shown, a method for generating a mobile collaborative electronic signature for phased authentication of the target product is disclosed. The method is implemented by a mobile terminal, a CA center, and a product authentication application data submission system server in collaboration, and includes the following steps: Step S201: The certification applicant registers an account on the product certification application information submission system server and uses the mobile phone number authenticated by the operator as the account user name.

[0061] Step S202: After the certification applicant logs into the product certification application information submission system through a mobile smart terminal, he / she performs personal identity authentication and enterprise real-name authentication respectively.

[0062] Step S203: After the authentication applicant completes the identity authentication of the corresponding role, a pair of public and private key factors are generated in the mobile smart terminal and the CA center respectively. After the mobile smart terminal sends the generated public key factor P1 to the CA center, P1 and the CA center's own public key P2 are synthesized into a public key P through point multiplication and other operations, and the synthesized public key P and the above account are used to generate a mobile signature digital certificate and an encrypted digital certificate.

[0063] Step S204: After the CA center confirms the identity of the authentication applicant's handler, it issues the authentication applicant's handler's mobile terminal signature digital certificate, encryption digital certificate and encryption private key to the authentication applicant's handler and records them on the mobile smart terminal side.

[0064] Step S205: After the certification applicant passes the identity authentication and successfully obtains the mobile terminal signature digital certificate and encryption digital certificate, the product certification application information submission system creates an electronic seal according to the digital certificate user subject information.

[0065] Step S206: After the certification applicant passes the identity authentication and uses the mobile smart terminal to log in to the product certification application information submission system, the certification applicant's electronic seal, mobile signature digital certificate, encrypted digital certificate and encrypted private key are embedded in the submitted product certification application materials to calculate and generate a mobile collaborative electronic signature.

[0066] Furthermore, the above method can be implemented in the form of a computer program on a product certification application information submission system server, comprising the following steps: Step 1: Obtain the signature digital certificate, encryption digital certificate and encryption private key of the applicant of the product certification application materials from the mobile terminal; wherein the signature digital certificate and the encryption digital certificate are generated by the CA center according to the synthetic public key and the product certification application materials submission system account; the synthetic public key is generated according to the first public key factor of the mobile terminal and the second public key factor of the CA center; Step 2: Create an electronic seal based on the applicant's principal information, and calculate and generate a mobile collaborative electronic signature based on the electronic seal, signature digital certificate, encryption digital certificate and encryption private key; Step three: embed the mobile collaborative electronic signature into the product certification application materials.

[0067] After the mobile collaborative electronic signature is generated, the person handling the certification application passes the identity authentication and uses the mobile smart terminal to log in to the product certification application materials submission system, and then previews the submitted product certification application materials. If the identity authentication is unauthorized, the preview of the submitted product certification application materials will not be possible. After the person handling the certification application passes the identity authentication and logs in to the product certification application materials submission system, the person handling the certification application downloads the submitted product certification application materials. If the identity authentication is unauthorized, the download of the submitted product certification application materials will not be possible. The product certification application materials submission system provides a product certification application materials verification function that is achieved through the verification of the mobile collaborative electronic signature. Failure of the mobile collaborative electronic signature verification indicates that the submitted product certification application materials have been tampered with or are illegal, and at this time it is prompted that the submitted product certification application materials are invalid.

[0068] The above method of generating a mobile collaborative electronic signature for the phased certification of the target product enables the certification applicant to perform role-based identity authentication on the basis of submitting the certification application materials, thereby ensuring the legal identity of the certification applicant. The certification applicant can quickly and conveniently complete the process of submitting the certification application materials, thereby ensuring the timeliness of the submission of the certification application materials. The security control of the review and downloading of the certification application materials is ensured through the identity authentication of the certification applicant. Provide a certification application materials legality verification service to ensure the post-verification of the legality of the certification application materials.

[0069] The product phased authentication method based on mobile collaborative electronic signature provided in this embodiment can intelligently determine whether the product meets the phased progress based on the authentication application materials and thus grant authentication, thereby improving the authentication efficiency and ensuring the security, timeliness, legality and convenience of submitting the authentication application materials.

[0070] Figure 3 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. Figure 3 , which shows a schematic diagram of the structure of an electronic device 300 suitable for implementing the embodiment of the present invention. The electronic device 300 in the embodiment of the present invention may include but is not limited to a product certification application data submission system server composed of a laptop computer, a PAD (tablet computer), a desktop computer, a dedicated server, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0071] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303 to implement the method of the embodiment of the present invention. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0072] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0073] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart, thereby implementing the method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.

[0074] In one embodiment, reference Figure 4 As shown, a product phased authentication device 400 based on mobile collaborative electronic signature is provided, and the device 400 includes: a first generation module 410, an acquisition module 420, an output module 430 and a second generation module 440; wherein, The first generating module 410 is used to receive product certification application materials of a target product and generate a first feature vector representing the core content of the product certification application materials; The acquisition module 420 is used to acquire a second feature vector of the index text representing the target product; wherein the index text is generated based on the first feature vector of the core content of each product certification application material completed by the target product and a plurality of R&D stage labels corresponding to the target product; the R&D stage label corresponding to the target product is determined according to the category of the target product; An output module 430 is used to input the first feature vector and the second feature vector into a pre-trained neural network model to obtain an output result; the output result is used to indicate whether the core content of the product certification application materials is added to the index text; The second generation module 440 is used to generate a mobile collaborative electronic signature for phased authentication of the target product if the output result is yes.

[0075] Optionally, the first generation module 410 is further used to segment the product certification application materials to obtain at least one text segment; for each of the text segments, obtain the corresponding previous text segment and the summary vector of the previous text segment, the previous text segment is all the text segments before the text segment in the product certification application materials, concatenate the summary vector of the previous text segment and the feature vector of the text segment to obtain the summary vector of the text segment; based on the summary vectors corresponding to each of the text segments, generate a first feature vector representing the core content of the product certification application materials.

[0076] Optionally, the first generation module 410 is further used to, for each of the images, input the image into a generative model to obtain a description text of the image; in the product certification application materials, determine a target text segment related to the image, and integrate the description text with the target text segment.

[0077] Optionally, the first generation module 410 is further used to identify the picture to obtain a text recognition result; determine the image quality of the picture based on the image feature vector of the picture, and the image quality is used to characterize the clarity of the picture; input the text recognition result, the image feature vector and the image quality score into a pre-trained generative model to obtain a description text of the picture; the image quality score is used to determine the participation weight of the text recognition result when the generative model understands the picture.

[0078] Optionally, the index module 420 is further used to set multiple nodes of the index text according to each of the R&D stage labels; determine the explanatory text of each of the nodes and generate a third feature vector of the explanatory text, the explanatory text is used to characterize the key features of the target product required by each node; calculate the similarity between the third feature vector of each explanatory text and the first feature vector of the core content of each completed product certification application material, and obtain the target product certification application material under each of the nodes; for each of the nodes, generate the index text according to the core content of the target product certification application material under the node.

[0079] Optionally, the index module 420 is further used to determine search keywords and at least one genre search intent based on the R&D stage label corresponding to each node; search according to the search keywords to obtain multiple multimedia information corresponding to the genre search intent; perform multimodal understanding on the multiple multimedia information to determine the explanatory text of each of the nodes.

[0080] Optionally, if the output result is yes, it includes: the output result is used to characterize whether the core content of the product certification application materials corresponds to the first target node of the index text, and the corresponding target product certification application materials do not exist under the first target node; or, the output result is used to characterize whether the core content of the product certification application materials corresponds to the second target node of the index text, and the corresponding target product certification application materials exist under the second target node, and the core content of the product certification application materials is used to update the second target node.

[0081] Optionally, the second generation module 440 is further used to: obtain the signature digital certificate, encryption digital certificate and encryption private key of the applicant of the product certification application materials from the mobile terminal; wherein the signature digital certificate and the encryption digital certificate are generated by the CA center based on the synthetic public key and the product certification application materials reporting system account; the synthetic public key is generated based on the first public key factor of the mobile terminal and the second public key factor of the CA center; create an electronic seal based on the applicant's subject information, and calculate and generate a mobile collaborative electronic signature based on the electronic seal, signature digital certificate, encryption digital certificate and encryption private key; and implant the mobile collaborative electronic signature in the product certification application materials.

[0082] It should be noted that the product phased authentication device 400 based on mobile collaborative electronic signature provided in the embodiment of the present invention corresponds to the technical solution that can be used to execute the above-mentioned method embodiments, and its implementation principle and technical effect are similar, which will not be repeated here.

[0083] In one embodiment, a computer-readable medium is provided, which carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device can implement the following functions: Receive product certification application materials of a target product, and generate a first feature vector representing the core content of the product certification application materials; obtain a second feature vector representing an index text of the target product; wherein the index text is generated based on the first feature vector of the core content of each completed product certification application material of the target product and a plurality of R&D stage labels corresponding to the target product; the R&D stage label corresponding to the target product is determined according to the category of the target product; input the first feature vector and the second feature vector into a pre-trained neural network model to obtain an output result; the output result is used to represent whether the core content of the product certification application materials is added to the index text; if the output result is yes, generate a mobile collaborative electronic signature for the phased certification of the target product.

[0084] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) to form a technical solution.

Claims

1. A product phased authentication method based on mobile collaborative electronic signature, characterized in that: The method comprises: Receiving product certification application materials of a target product, and generating a first feature vector representing the core content of the product certification application materials; Obtaining a second feature vector of an index text representing the target product; wherein the index text is generated based on a first feature vector of the core content of each product certification application material completed by the target product and a plurality of R&D stage labels corresponding to the target product; the R&D stage label corresponding to the target product is determined according to the category of the target product; Inputting the first feature vector and the second feature vector into a pre-trained neural network model to obtain an output result; the output result is used to indicate whether the core content of the product certification application materials is added to the index text; If the output result is yes, a mobile collaborative electronic signature for phased authentication of the target product is generated.

2. According to claim 1, a product phased authentication method based on mobile collaborative electronic signature is characterized in that: The product certification application materials include text, and the generating of a first feature vector representing the core content of the product certification application materials includes: Segmenting the product certification application materials to obtain at least one text segment; For each of the text segments, obtain the previous text segment corresponding to the text segment and the summary vector of the previous text segment, wherein the previous text segment is all text segments before the text segment in the product certification application materials, and concatenate the summary vector of the previous text segment and the feature vector of the text segment to obtain the summary vector of the text segment; A first feature vector representing the core content of the product certification application materials is generated according to the summary vector corresponding to each of the text segments.

3. According to claim 2, a product phased authentication method based on mobile collaborative electronic signature is characterized in that: The product certification application materials include pictures, and the method further includes: For each of the pictures, input the picture into the generative model to obtain a description text of the picture; In the product certification application materials, a target text segment related to the image is determined, and the description text is integrated with the target text segment.

4. According to claim 3, a product phased authentication method based on mobile collaborative electronic signature is characterized in that: The image is input into the generative model to obtain a description text of the image, including: Recognize the picture to obtain a text recognition result; Determining the image quality of the picture based on the image feature vector of the picture, where the image quality is used to characterize the clarity of the picture; The text recognition result, the image feature vector and the image quality score are input into a pre-trained generative model to obtain a description text of the image; the image quality score is used to determine the participation weight of the text recognition result when the generative model understands the image.

5. A product phased authentication method based on mobile collaborative electronic signature according to any one of claims 1 to 4, characterized in that: The index text is generated based on the first feature vector of the core content of each product certification application material completed by the target product and multiple R&D stage labels corresponding to the target product, specifically including: Setting a plurality of nodes of the index text according to each of the research and development stage labels; Determine an explanation text of each of the nodes and generate a third feature vector of the explanation text, wherein the explanation text is used to characterize key features of the target product required by each node; Calculate the similarity between the third feature vector of each interpretation text and the first feature vector of the core content of each completed product certification application document to obtain the target product certification application document under each node; For each of the nodes, the index text is generated according to the core content of the target product certification application materials under the node.

6. A product phased authentication method based on mobile collaborative electronic signature according to claim 5, characterized in that: The step of determining the interpretation text of each node comprises: Determine a search keyword and at least one genre search intent based on the R&D stage label corresponding to each node; Searching according to the search keyword to obtain a plurality of multimedia information corresponding to the genre search intention; The plurality of multimedia information are subjected to multimodal understanding to determine an explanation text of each of the nodes.

7. A product phased authentication method based on mobile collaborative electronic signature according to claim 5, characterized in that: If the output result is yes, it includes: The output result is used to indicate whether the core content of the product certification application document corresponds to the first target node of the index text, and the corresponding target product certification application document does not exist under the first target node; or, The output result is used to characterize whether the core content of the product certification application materials corresponds to the second target node of the index text, and the corresponding target product certification application materials exist under the second target node. The core content of the product certification application materials is used to update the second target node.

8. According to claim 1, a product phased authentication method based on mobile collaborative electronic signature is characterized by: The step of generating the mobile collaborative electronic signature for the phased authentication of the target product specifically includes: Obtain the signature digital certificate, encryption digital certificate and encryption private key of the applicant of the product certification application materials from the mobile terminal; wherein the signature digital certificate and the encryption digital certificate are generated by the CA center according to the synthetic public key and the product certification application materials submission system account; the synthetic public key is generated according to the first public key factor of the mobile terminal and the second public key factor of the CA center; Creating an electronic seal according to the applicant's principal information, and calculating and generating a mobile collaborative electronic signature according to the electronic seal, signature digital certificate, encryption digital certificate and encryption private key; The mobile collaborative electronic signature is implanted in the product certification application materials.

9. A product phased authentication device based on mobile collaborative electronic signature, characterized in that: include: A first generating module, configured to receive product certification application materials of a target product and generate a first feature vector representing the core content of the product certification application materials; An acquisition module, used to acquire a second feature vector of an index text representing the target product; wherein the index text is generated based on a first feature vector of the core content of each product certification application material completed by the target product and a plurality of R&D stage labels corresponding to the target product; the R&D stage label corresponding to the target product is determined according to the category of the target product; An output module, used for inputting the first feature vector and the second feature vector into a pre-trained neural network model to obtain an output result; the output result is used to indicate whether the core content of the product certification application materials is added to the index text; The second generation module is used to generate a mobile collaborative electronic signature for phased authentication of the target product if the output result is yes.

10. A product phased authentication device based on mobile collaborative electronic signature according to claim 9, characterized in that: The second generating module is further used for: Obtain the signature digital certificate, encryption digital certificate and encryption private key of the applicant of the product certification application materials from the mobile terminal; wherein the signature digital certificate and the encryption digital certificate are generated by the CA center according to the synthetic public key and the product certification application materials submission system account; the synthetic public key is generated according to the first public key factor of the mobile terminal and the second public key factor of the CA center; Creating an electronic seal according to the applicant's principal information, and calculating and generating a mobile collaborative electronic signature according to the electronic seal, signature digital certificate, encryption digital certificate and encryption private key; The mobile collaborative electronic signature is implanted in the product certification application materials.

Images