Text abstract generation method and system based on edge computing power

Abstract

The invention discloses a text abstract generation method and system based on edge computing power, and the method comprises the steps: obtaining the position information of a request when a text abstract generation request is received, and determining a nearest target edge server from a plurality of edge servers according to the position information; forwarding corresponding text data which needs to be subjected to text summarization to generate to the target edge server, analyzing the text data by utilizing the target edge server to obtain keywords of the text data, and preprocessing the text data to obtain text segments; and sending the keywords and the text fragments to a cloud server, analyzing the keywords and the text fragments by using the cloud server to obtain corresponding text abstracts, and transmitting the text abstracts to an edge server so as to push the text abstracts to corresponding users. The problem that in the prior art, when text abstract generation is conducted, the calculation pressure is large when generation tasks are concentrated is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of text generation, and in particular to a text summary generation method and system based on edge computing power. Background Art

[0002] With the rapid development of information technology, text data has exploded, and people are exposed to massive amounts of text information such as documents, news reports, academic papers, and social media posts every day. Text summarization technology has emerged to simplify long text content into short summaries that reflect the core points of the original text, so as to help users quickly obtain key information, save reading time, and improve information processing efficiency.

[0003] Currently, the generation of text summaries completely relies on cloud servers. These servers usually have powerful computing resources, which can process large amounts of data and generate high-quality text summaries. High-quality summaries are generated using deep learning and natural language processing algorithms (such as BERT, GPT and other models).

[0004] However, when a large amount of data needs to be uploaded to the cloud server for processing, the cloud server has to process a large amount of data at the same time, resulting in high pressure on background processing and computing. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide a text summary generation method and system based on edge computing power, aiming to solve the problem in the prior art of high computing pressure when generating text summaries when the generation tasks are relatively concentrated.

[0006] The embodiment of the present invention is implemented as follows: On the one hand, a text summary generation method based on edge computing power is proposed, which is applied to the scenario of using edge computing power to realize text summary generation, wherein a grid architecture including a cloud server and multiple edge servers is set, and the cloud server is communicated with the edge server. The method includes: When a text summary generation request is received, obtaining location information of the request, and determining the closest target edge server from among multiple edge servers according to the location information; Forwarding the text data corresponding to the text summary generation to the target edge server, using the target edge server to analyze the text data to obtain keywords of the text data, and preprocessing the text data to obtain text fragments; The keywords and text fragments are sent to the cloud server, and the cloud server is used to analyze the keywords and text fragments to obtain corresponding text summaries, and the text summaries are transmitted to the edge server to be pushed to the corresponding users.

[0007] Furthermore, in the above-mentioned method for generating text summaries based on edge computing power, the step of using the target edge server to analyze the text data to obtain keywords of the text data, and preprocessing the text data to obtain text fragments includes: Performing word frequency statistics on the text data or obtaining keywords of the text data using a rule-based keyword extractor; The text data is subjected to noise removal and the basic structure of the text data is identified to obtain text fragments.

[0008] Furthermore, in the above-mentioned method for generating text summaries based on edge computing power, the step of using a cloud server to analyze the keywords and text fragments to obtain corresponding text summaries also includes: Filter out relevant fragments based on the similarity between keywords and text fragments and the location information of the text; Marking the parts of speech of the text words corresponding to the text of the relevant fragments, and identifying the dependency relationship between the text words corresponding to the text of the relevant fragments based on the parts of speech; Based on the dependency relationship, analyzing the sentence structure of the text of the related fragment, and based on the sentence structure, extracting the sentence features of the text of the related fragment; Based on the sentence features, the corresponding text summary is output using the preset language summary model.

[0009] Furthermore, in the above-mentioned method for generating text summaries based on edge computing power, the step of sending the keywords and text fragments to a cloud server, analyzing the keywords and text fragments using the cloud server to obtain corresponding text summaries, and transmitting the text summaries to the edge server to push them to the corresponding user image also includes: An encryption key is generated according to a preset rule, and the keywords and text fragments are encrypted and transmitted using the encryption key.

[0010] Furthermore, in the above-mentioned method for generating a text summary based on edge computing power, the step of generating an encryption key according to a preset rule includes: The timestamps of obtaining the keywords and the text fragments, as well as the number of keywords and the number of sentences in the text fragments, form a digital encryption element; Obtain the pinyin characters of the keyword to determine the letter encryption element, and perform hash operations on the digital encryption element and the letter encryption element to obtain a first hash value and a second hash value; The final encryption key is determined according to the first Hash value and the second Hash value according to a preset rule.

[0011] Furthermore, in the above-mentioned text summary generation method based on edge computing power, the step of determining the final encryption key according to the first hash value and the second hash value according to a preset rule includes: The first hash value and the second hash value are concatenated to obtain a target hash value, and a modulus operation is performed on the target hash value to obtain a preliminary key seed; The key seed is used to generate a fixed-length sequence through a pseudo-random number generator to obtain the final encryption key.

[0012] Furthermore, in the above-mentioned method for generating a text summary based on edge computing power, the step of determining the final encryption key according to the first hash value and the second hash value according to a preset rule further includes: Convert the first hash value and the second hash value into numerical values; The length of the minor axis is determined according to one of the first Hash value and the second Hash value after numerical conversion, and the length of the major axis is determined by the sum of the first Hash value and the second Hash value to obtain an elliptic curve which is determined as an encryption key determination curve; A reference point is randomly determined on the encryption key determination curve, numerical information of the reference point is obtained, and the numerical information is inversely converted to obtain the encryption key; Among them, the elliptic curve is mapped to the coordinate system according to the distance between the set coordinate origin and the center position of the elliptic curve, so as to determine the coordinates of the reference point, and the value corresponding to the sum of the horizontal and vertical coordinates of the reference point coordinates is obtained and then the inverse numerical conversion is performed.

[0013] Another object of the present invention is to provide a text summary generation system based on edge computing power, which is applied to the scenario of using edge computing power to realize text summary generation, wherein a grid architecture including a cloud server and multiple edge servers is set, and the cloud server is communicatively connected with the edge server, and the system includes: An acquisition module, configured to, when receiving a text summary generation request, acquire location information of the request, and determine the closest target edge server from among multiple edge servers according to the location information; An analysis module is used to forward the text data corresponding to the text summary generation to the target edge server, analyze the text data using the target edge server to obtain keywords of the text data, and pre-process the text data to obtain text fragments; The generation module is used to send the keywords and text fragments to the cloud server, and use the cloud server to analyze the keywords and text fragments to obtain corresponding text summaries, and transmit the text summaries to the edge server to push them to the corresponding users.

[0014] In yet another aspect, the present invention provides a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.

[0015] In yet another aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0016] The embodiment of the present invention sets up multiple edge servers to communicate with the cloud server. When performing the text summary generation task, some simple processing tasks of text data preprocessing can be performed in the edge server, which can reduce the need to transmit some data to the cloud, help alleviate the computing pressure and bandwidth requirements of the cloud, and then further process in the cloud server to ensure the quality of text summary generation. This solves the problem of high computing pressure in the prior art when facing concentrated generation tasks when performing text summary generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flowchart of the text summary generation method based on edge computing power proposed in the first embodiment of the present invention; Figure 2 Schematic diagram of the structure of the text summary generation system based on edge computing power in the third embodiment of the present invention.

[0018] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0019] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0020] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0022] The following will explain in detail how to improve the accuracy of Mini LED solder joint defect detection in combination with specific embodiments and drawings.

[0023] Embodiment 1 See also Figure 1 , shown is a text summary generation method based on edge computing power proposed in the first embodiment of the present invention, which is applied to the scenario of using edge computing power to realize text summary generation, wherein a grid architecture including a cloud server and multiple edge servers is set, and the cloud server is communicatively connected with the edge server, and the method includes steps S10~S12.

[0024] Step S10: when a text summary generation request is received, the location information of the request is obtained, and the closest target edge server is determined from among multiple edge servers according to the location information.

[0025] Among them, in order to solve the problem of high computing pressure when processing text summary generation through cloud servers alone when facing concentrated tasks, a grid architecture including cloud servers and multiple edge servers is adopted. It connects cloud servers and edge servers to form a whole to jointly process tasks. Specifically, the cloud server is the core part of the grid architecture, which usually has powerful computing power and storage capacity. In the scenario of text summary generation, the cloud server is responsible for receiving data from the edge server, performing complex calculations and analysis, generating the final summary result, and returning the result to the requester; while the edge server is located at the edge of the network, that is, closer to the user or data source. In the scenario of text summary generation, the edge server is responsible for tasks such as preliminary text preprocessing. Since the edge server is closer to the data source, it can respond and process data faster, reduce data transmission delays and bandwidth occupancy, and share the computing pressure of the cloud server.

[0026] Furthermore, when a user or a system needs to generate a text summary, a text summary generation request is sent. This text summary generation request contains at least the text content to be summarized. After receiving the request, the location information from which the request was sent is obtained. This location information can be a geographic coordinate (such as longitude and latitude) or a more abstract network location identifier (such as the region to which the IP address belongs). The purpose of obtaining the location information is to determine the geographic location of the request source so that the most suitable edge server can be selected to process the request later. After obtaining the location information of the request, multiple available edge servers are traversed, and the distance between each server and the request source is calculated based on the geographic location of each server (known in advance or obtained in real time). This distance can be a physical distance or a more comprehensive measure such as network delay. Then, the edge server closest to the request source is selected as the target edge server. Selecting the closest edge server is usually to reduce data transmission delays and increase processing speed.

[0027] Step S11, forwarding the text data corresponding to the text summary generation to the target edge server, using the target edge server to analyze the text data to obtain keywords of the text data, and preprocessing the text data to obtain text fragments.

[0028] After determining the target edge server for processing the request, the text data that needs to be summarised will be forwarded to this server. After receiving the text data, the target edge server will perform a preliminary analysis on it. One of the purposes of the analysis is to identify keywords in the text data. Keywords are important or frequently appearing words in the text. They can usually summarize the theme or core content of the text. After obtaining the keywords, the target edge server will also pre-process the text data. The purpose of pre-processing is to convert the text data into units that are easier to process. These units are called text fragments.

[0029] Specifically, word frequency statistics or rule-based keyword extractors are used to obtain keywords from text data. Word frequency statistics is a simple and effective keyword extraction method. It identifies the most frequently occurring words in the text by counting the number of times each word appears in the text data. Rule-based keyword extractors use predefined rules or patterns to identify keywords in the text. Pre-processing operations include but are not limited to denoising the text data. Noise may include insignificant words (such as stop words), redundant punctuation marks, numbers, special characters, etc. Removing noise helps reduce the complexity of text data and improve the efficiency and accuracy of subsequent processing. After removing noise, it is necessary to identify the basic structure of the text data, including titles, text, paragraphs, and quoted parts. These operations provide basic data for subsequent text summary generation.

[0030] Step S12, sending the keywords and text fragments to the cloud server, and using the cloud server to analyze the keywords and text fragments to obtain corresponding text summaries, and transmitting the text summaries to the edge server to push to the corresponding users.

[0031] After completing the preprocessing of the text data, the edge server will send the extracted keywords and segmented text fragments to the cloud server. After receiving the keywords and text fragments, the cloud server will use advanced natural language processing technology and algorithms to conduct in-depth analysis of these data. Once the text summary is generated, the cloud server will transmit it back to the edge server. After receiving the text summary, the edge server will push the summary to the corresponding user based on the information provided in the request (such as user ID, device information, etc.). This process fully utilizes the advantages of edge computing and cloud computing to achieve efficient and accurate text summary generation and push.

[0032] Specifically, the step of using the cloud server to analyze the keywords and text segments to obtain corresponding text summaries also includes: Filter out relevant fragments based on the similarity between keywords and text fragments and the location information of the text; Marking the parts of speech of the text words corresponding to the text of the relevant fragments, and identifying the dependency relationship between the text words corresponding to the text of the relevant fragments based on the parts of speech; Based on the dependency relationship, analyzing the sentence structure of the text of the related fragment, and based on the sentence structure, extracting the sentence features of the text of the related fragment; Based on the sentence features, the corresponding text summary is output using the preset language summary model.

[0033] Among them, the cloud server will first analyze the similarity between the keywords and each text fragment, which can be achieved by calculating the frequency of occurrence of the keywords in the fragments, TF-IDF values, etc. At the same time, the position information of the text fragment in the original text (such as the beginning, end, title, etc. of the paragraph) will also be considered, because these positions often contain more important information. Based on the comprehensive evaluation of similarity and position information, the text fragments that are most relevant to the keywords and have the largest amount of information are screened out, and the screened relevant fragments are tagged with parts of speech, that is, the part of speech of each word (such as noun, verb, adjective, etc.) is identified. Based on the part-of-speech tagging results, the dependency relationship between words, such as subject-predicate relationship, verb-object relationship, etc., is further analyzed. This helps to understand the grammatical structure and semantic information of the sentence. The results of dependency analysis are used to divide the sentence structure of the text fragment, identify the main body and modifying components of the sentence, and extract the features of each sentence based on the sentence structure. These features may include key information such as the subject, predicate, and object of the sentence. The extracted sentence features are used as input and sent to the preset language summary model. The language summary model will generate the corresponding text summary based on these features and the knowledge learned within the model. For example, the language summary model can use the BERT model. These models are pre-trained on a large amount of text data and have learned rich language knowledge and context understanding capabilities. By fine-tuning these models, they can be adapted to text summary tasks and generate high-quality summaries.

[0034] In summary, the text summary generation method based on edge computing in the above embodiment of the present invention, by setting up multiple edge servers to communicate with the cloud server, can perform some simple processing tasks of text data preprocessing in the edge server when performing the text summary generation task, which can reduce the need to transmit part of the data to the cloud, help to reduce the computing pressure and bandwidth requirements of the cloud, and then further process in the cloud server to ensure the quality of text summary generation. This solves the problem of high computing pressure in the prior art when generating text summaries when the generation tasks are relatively concentrated.

[0035] Embodiment 2 This embodiment also proposes a text summary generation method based on edge computing power. The difference between the text summary generation method based on edge computing power proposed in this embodiment and the text summary generation method based on edge computing power proposed in the first embodiment is that: The step of sending the keywords and text segments to a cloud server, analyzing the keywords and text segments using the cloud server to obtain corresponding text summaries, and transmitting the text summaries to an edge server to push to a corresponding user image also includes: An encryption key is generated according to a preset rule, and the keywords and text fragments are encrypted and transmitted using the encryption key.

[0036] Among them, in order to ensure the security of data transmission, before the transmission of keywords and text fragments begins, an encryption key will be generated according to preset rules or algorithms; this encryption key prevents unauthorized access or data leakage. When the encryption key is generated, the system will use this key to encrypt the keywords and text fragments. The encrypted keywords and text fragments will be securely transmitted to the cloud server. After the cloud server receives the encrypted keywords and text fragments, it will use the corresponding key to decrypt them. After decryption, the cloud server will analyze the keywords and text fragments according to the established steps, and generate the corresponding text summary and transmit it back to the edge server. When transmitting back to the edge server, the corresponding encryption key can also be generated for encryption.

[0037] Specifically, the step of generating an encryption key according to a preset rule includes: The timestamps of obtaining the keywords and the text fragments, as well as the number of keywords and the number of sentences in the text fragments, form a digital encryption element; Obtain the pinyin characters of the keyword to determine the letter encryption element, and perform hash operations on the digital encryption element and the letter encryption element to obtain a first hash value and a second hash value; The final encryption key is determined according to the first Hash value and the second Hash value according to a preset rule.

[0038] First, obtain the timestamp of the keyword and text fragment acquisition (i.e. the time point when the data is processed or requested). Next, count the number of keywords and the number of sentences in the text fragment. This information reflects certain characteristics of the data and can be used as part of generating the encryption key. Combine the timestamp, the number of keywords, and the number of sentences in the text fragment to form a digital encryption element. This element is a set or sequence containing multiple digital values; on the other hand, obtain the pinyin characters of the keywords. Here, it is assumed that the keywords are Chinese words, so they are converted into pinyin form to obtain the letter sequence. Pinyin characters are used as letter encryption elements. They represent the pronunciation of keywords, which increases the complexity and randomness of the encryption key; perform a hash operation on the digital encryption element to obtain a first hash value. Hashing is a process of converting data of arbitrary length into a fixed-length hash value, which is irreversible and collision-resistant. Perform a hash operation on the letter encryption element to obtain a second hash value. The same hash function or different hash functions can be used here. Finally, the target hash value used for encryption is determined based on the first hash value and the second hash value, and the hash value is used as the encryption key.

[0039] Exemplarily, the first hash value and the second hash value are concatenated to obtain a target hash value, and a modulus operation is performed on the target hash value to obtain a preliminary key seed; The key seed is used to generate a fixed-length sequence through a pseudo-random number generator to obtain the final encryption key.

[0040] Among them, the two hash values ​​are concatenated, that is, they are connected together in a certain order to form a longer hash value sequence, which is called the target hash value. A suitable modulus is selected, and then the target hash value is modulo-operated. The result of the modulo operation is a smaller value, which is used as a preliminary key seed. The purpose of the modulo operation is to shorten the target hash value, which may be very long, to a more manageable length while retaining sufficient randomness. A pseudo-random number generator (PRNG) is used, and the preliminary key seed is used as input. The pseudo-random number generator generates a pseudo-random sequence based on the key seed. This sequence has a certain length, which corresponds to the length of the required encryption key. A fixed-length part is extracted from this pseudo-random sequence, which is the final encryption key.

[0041] In addition, in order to further improve the security of the encryption key, in some optional embodiments of the present invention, the step of determining the final encryption key according to the first Hash value and the second Hash value according to a preset rule further includes: Convert the first hash value and the second hash value into numerical values; The length of the minor axis is determined according to one of the first Hash value and the second Hash value after numerical conversion, and the length of the major axis is determined by the sum of the first Hash value and the second Hash value to obtain an elliptic curve which is determined as an encryption key determination curve; A reference point is randomly determined on the encryption key determination curve, numerical information of the reference point is obtained, and the numerical information is inversely converted to obtain the encryption key.

[0042] Among them, the first hash value and the second hash value are numerically converted. The binary representation of the hash value is converted to decimal and then normalized and linearly scaled. The purpose of the numerical conversion is to map the hash value to a mathematical domain suitable for subsequent processing. The short axis length of the elliptic curve is determined according to the first hash value or the second hash value after the numerical conversion, and the sum of the first hash value and the second hash value is calculated, and this sum is used as the long axis length of the elliptic curve. Through these two length parameters, a specific elliptic curve can be determined, and a point is randomly selected as a reference point on the determined elliptic curve. The selection of this point is random to ensure the unpredictability of the generated encryption key. The numerical information of this reference point is obtained, including the coordinates of the point or related mathematical parameters. In this embodiment, the coordinates of the point can be obtained, and the numerical value corresponding to the reference point can be determined according to the sum of the horizontal and vertical coordinates of the coordinates. In specific implementation, the elliptic curve can be projected (mapped) into the coordinate system according to the distance between the set coordinate origin and the center position of the elliptic curve, so that the coordinates of the point can be determined. After the numerical value corresponding to the reference point is determined, the reverse numerical conversion is performed, that is, the numerical conversion process previously performed is reversed to obtain the final encryption key, wherein the "distance between the coordinate origin and the center position of the elliptic curve" refers to the straight-line distance from the origin of the coordinate system to the center of the elliptic curve (i.e., the geometric center of the ellipse). Based on the above distance information, the entire elliptic curve can be "placed" or "mapped" into a two-dimensional coordinate system. The elliptic curve is mapped to the coordinate system, and a point on the ellipse can be selected as the reference point. The coordinates of the reference point are the specific position of the point in the coordinate system.

[0043] In addition, in some optional embodiments of the present invention, number theory and modular operations can be used for encryption, the first hash value, the second hash value, and the target hash value are used as key seeds, each key seed is regarded as the remainder of a congruence equation, and the large integer of the hardware serial number of the edge server is used as the modulus to construct a congruence equation group. Solving this equation group can obtain a unique solution, which is used as the encryption key.

[0044] In summary, the text summary generation method based on edge computing power proposed in the above embodiment of the present invention, by setting up multiple edge servers to communicate with the cloud server, can perform some simple processing tasks of text data preprocessing in the edge server when performing the text summary generation task, which can reduce the need to transmit part of the data to the cloud, help to reduce the computing pressure and bandwidth requirements of the cloud, and then further process in the cloud server to ensure the quality of text summary generation. This solves the problem of high computing pressure in the prior art when generating text summaries when the generation tasks are relatively concentrated.

[0045] Embodiment 3 See also Figure 2, shown is a text summary generation system based on edge computing power proposed in the third embodiment of the present invention, which is applied to the scenario of using edge computing power to realize text summary generation, wherein a grid architecture including a cloud server and multiple edge servers is set, and the cloud server is communicatively connected with the edge server, and the system includes: The acquisition module 100 is used to, when receiving a text summary generation request, acquire location information of the request, and determine the closest target edge server from multiple edge servers according to the location information; The analysis module 200 is used to forward the text data corresponding to the text summary generation to the target edge server, analyze the text data by the target edge server to obtain the keywords of the text data, and pre-process the text data to obtain text fragments; The generation module 300 is used to send the keywords and text fragments to the cloud server, and use the cloud server to analyze the keywords and text fragments to obtain corresponding text summaries, and transmit the text summaries to the edge server to push them to the corresponding users.

[0046] Furthermore, in the above-mentioned text summary generation system based on edge computing power, the step of using the target edge server to analyze the text data to obtain keywords of the text data, and preprocessing the text data to obtain text fragments includes: Performing word frequency statistics on the text data or obtaining keywords of the text data using a rule-based keyword extractor; The text data is subjected to noise removal and the basic structure of the text data is identified to obtain text fragments.

[0047] Furthermore, in the above-mentioned text summary generation system based on edge computing power, the step of using the cloud server to analyze the keywords and text fragments to obtain corresponding text summaries also includes: Filter out relevant fragments based on the similarity between keywords and text fragments and the location information of the text; Marking the parts of speech of the text words corresponding to the text of the relevant fragments, and identifying the dependency relationship between the text words corresponding to the text of the relevant fragments based on the parts of speech; Based on the dependency relationship, analyzing the sentence structure of the text of the related fragment, and based on the sentence structure, extracting the sentence features of the text of the related fragment; Based on the sentence features, the corresponding text summary is output using the preset language summary model.

[0048] Furthermore, in the above-mentioned text summary generation system based on edge computing power, the step of sending the keywords and text fragments to the cloud server, analyzing the keywords and text fragments by the cloud server to obtain corresponding text summaries, and transmitting the text summaries to the edge server to push them to the corresponding user image also includes: An encryption key is generated according to a preset rule, and the keywords and text fragments are encrypted and transmitted using the encryption key.

[0049] Furthermore, in the above-mentioned text summary generation system based on edge computing power, the step of generating an encryption key according to a preset rule includes: The timestamps of obtaining the keywords and the text fragments, as well as the number of keywords and the number of sentences in the text fragments, form a digital encryption element; Obtain the pinyin characters of the keyword to determine the letter encryption element, and perform hash operations on the digital encryption element and the letter encryption element to obtain a first hash value and a second hash value; The final encryption key is determined according to the first Hash value and the second Hash value according to a preset rule.

[0050] Furthermore, in the above-mentioned text summary generation system based on edge computing power, the step of determining the final encryption key according to the first hash value and the second hash value according to a preset rule includes: The first hash value and the second hash value are concatenated to obtain a target hash value, and a modulus operation is performed on the target hash value to obtain a preliminary key seed; The key seed is used to generate a fixed-length sequence through a pseudo-random number generator to obtain the final encryption key.

[0051] Furthermore, in the above-mentioned text summary generation system based on edge computing power, the step of determining the final encryption key according to the first hash value and the second hash value according to a preset rule also includes: Convert the first hash value and the second hash value into numerical values; The length of the minor axis is determined according to one of the first Hash value and the second Hash value after numerical conversion, and the length of the major axis is determined by the sum of the first Hash value and the second Hash value to obtain an elliptic curve which is determined as an encryption key determination curve; A reference point is randomly determined on the encryption key determination curve, numerical information of the reference point is obtained, and the numerical information is inversely converted to obtain the encryption key; Among them, the elliptic curve is mapped to the coordinate system according to the distance between the set coordinate origin and the center position of the elliptic curve, so as to determine the coordinates of the reference point, and the value corresponding to the sum of the horizontal and vertical coordinates of the reference point coordinates is obtained and then the inverse numerical conversion is performed.

[0052] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments, and will not be repeated here.

[0053] Embodiment 4 Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the method described in any one of the above embodiments 1 to 2 are implemented.

[0054] Embodiment 5 Another aspect of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the above-mentioned embodiments 1 to 2 when executing the program.

[0055] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0056] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable storage medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0057] More specific examples (a non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0058] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0059] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0060] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A text summary generation method based on edge computing power, characterized in that: Applied to the scenario of using edge computing power to realize text summary generation, wherein a grid architecture including a cloud server and multiple edge servers is set, and the cloud server is communicatively connected with the edge server, and the method includes: When a text summary generation request is received, obtaining location information of the request, and determining the closest target edge server from among multiple edge servers according to the location information; Forwarding the text data corresponding to the text summary generation to the target edge server, using the target edge server to analyze the text data to obtain keywords of the text data, and preprocessing the text data to obtain text fragments; The keywords and text fragments are sent to the cloud server, and the cloud server is used to analyze the keywords and text fragments to obtain corresponding text summaries, and the text summaries are transmitted to the edge server to be pushed to the corresponding users.

2. The text summary generation method based on edge computing according to claim 1 is characterized in that: The step of using the target edge server to analyze the text data to obtain keywords of the text data, and preprocessing the text data to obtain text segments includes: Perform word frequency statistics on the text data or use a rule-based keyword extractor to obtain keywords from the text data; The text data is subjected to noise removal and the basic structure of the text data is identified to obtain text fragments.

3. The text summary generation method based on edge computing according to claim 2 is characterized in that: The step of using the cloud server to analyze the keywords and text segments to obtain corresponding text summaries also includes: Filter out relevant fragments based on the similarity between keywords and text fragments and the location information of the text; Marking the parts of speech of the text words corresponding to the text of the relevant fragments, and identifying the dependency relationship between the text words corresponding to the text of the relevant fragments based on the parts of speech; Based on the dependency relationship, analyzing the sentence structure of the text of the related fragment, and based on the sentence structure, extracting the sentence features of the text of the related fragment; Based on the sentence features, the corresponding text summary is output using the preset language summary model.

4. The text summary generation method based on edge computing according to claim 1 is characterized in that: The step of sending the keywords and text segments to a cloud server, analyzing the keywords and text segments using the cloud server to obtain corresponding text summaries, and transmitting the text summaries to an edge server to push to a corresponding user image also includes: An encryption key is generated according to a preset rule, and the keywords and text fragments are encrypted and transmitted using the encryption key.

5. The text summary generation method based on edge computing according to claim 4 is characterized in that: The step of generating an encryption key according to a preset rule comprises: The timestamps of obtaining the keywords and the text fragments, as well as the number of keywords and the number of sentences in the text fragments, form a digital encryption element; Obtain the pinyin characters of the keyword to determine the letter encryption element, and perform hash operations on the digital encryption element and the letter encryption element to obtain a first hash value and a second hash value; The final encryption key is determined according to the first Hash value and the second Hash value according to a preset rule.

6. The text summary generation method based on edge computing according to claim 5 is characterized in that: The step of determining the final encryption key according to the first Hash value and the second Hash value according to a preset rule comprises: The first hash value and the second hash value are concatenated to obtain a target hash value, and a modulus operation is performed on the target hash value to obtain a preliminary key seed; The key seed is used to generate a fixed-length sequence through a pseudo-random number generator to obtain the final encryption key.

7. The text summary generation method based on edge computing according to claim 5 is characterized in that: The step of determining the final encryption key according to the first Hash value and the second Hash value according to a preset rule also includes: Convert the first hash value and the second hash value into numerical values; The length of the minor axis is determined according to one of the first Hash value and the second Hash value after numerical conversion, and the length of the major axis is determined by the sum of the first Hash value and the second Hash value to obtain an elliptic curve which is determined as an encryption key determination curve; A reference point is randomly determined on the encryption key determination curve, numerical information of the reference point is obtained, and the numerical information is inversely converted to obtain the encryption key; Among them, the elliptic curve is mapped to the coordinate system according to the distance between the set coordinate origin and the center position of the elliptic curve, so as to determine the coordinates of the reference point, and the value corresponding to the sum of the horizontal and vertical coordinates of the reference point coordinates is obtained and then the inverse numerical conversion is performed.

8. A text summary generation system based on edge computing power, characterized in that: Applied to the scenario of using edge computing power to realize text summary generation, wherein a grid architecture including a cloud server and multiple edge servers is set, and the cloud server is communicated with the edge server. The system includes: An acquisition module, configured to, when receiving a text summary generation request, acquire location information of the request, and determine the closest target edge server from among multiple edge servers according to the location information; An analysis module is used to forward the text data corresponding to the text summary generation to the target edge server, analyze the text data using the target edge server to obtain keywords of the text data, and pre-process the text data to obtain text fragments; The generation module is used to send the keywords and text fragments to the cloud server, and use the cloud server to analyze the keywords and text fragments to obtain corresponding text summaries, and transmit the text summaries to the edge server to push them to the corresponding users.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.

Images