Energy storage project file standard auditing method, device and equipment and storage medium

Abstract

The invention discloses an energy storage project file standard auditing method and device, equipment and a storage medium. The method comprises the steps of obtaining a target project file to be subjected to standard auditing in an energy storage project, and performing file phrase processing on the target project file to obtain project file phrases; for each project file clause, determining a clause comprehensive confidence score of the project file clause according to the project file clause and each predetermined standard specification term; when the clause comprehensive confidence score is smaller than a preset confidence score threshold value, it is determined that the project file clauses do not meet the specification requirement, and when each project file clause meets the specification requirement, it is determined that the target project file meets the specification requirement, so that cross-standard accurate consistency checking can be achieved, and the checking efficiency is improved. The subjectivity and the uncertainty of manual interpretation are effectively avoided, and the accuracy and the reliability of an audit conclusion are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of project specification auditing, and in particular to a method, device and equipment for specification auditing of energy storage project files and a storage medium. BACKGROUND

[0002] As a key link supporting energy transformation, the construction and safe operation of energy storage projects are of great importance. To ensure the safety, reliability and interoperability of energy storage systems, project implementation must strictly follow a series of international, national and regional technical standards, such as the national standard GB / T 36276 of China, the IEC 62933-5-2 of the International Electrotechnical Commission and the UL 9540A of North America. These standard systems are independent of each other, have numerous clauses and technical requirements that are different and overlapping, forming a complex technical specification matrix.

[0003] Currently, the compliance auditing of technical documents of energy storage projects (such as design schemes, safety evaluation reports and test certification files) is extremely dependent on manual work by experts in the field. The auditors need to manually search and compare the document content with multiple sets of standard texts, which not only consumes a lot of manpower and time, but also is prone to misjudgment, omission or inconsistent interpretation of key clauses due to the professional and ambiguous nature of the standard expressions and frequent updates, making it difficult to ensure the quality and efficiency of the auditing, which has become a major bottleneck restricting the rapid approval and landing of projects.

[0004] Therefore, the existing technology has the core pain points of low automation, great influence of human factors on auditing accuracy and difficulty in adapting to complex compliance scenarios with multiple standards. There is an urgent need for an intelligent solution that can deeply understand the semantics of standards, has reasoning ability and can provide accurate and consistent auditing opinions to fundamentally improve the efficiency and reliability of the compliance auditing of energy storage project documents. SUMMARY

[0005] The present application provides a method, device and equipment for specification auditing of energy storage project files to realize accurate and consistent checking across standards, effectively avoiding the subjectivity and uncertainty of manual interpretation and significantly improving the accuracy and reliability of the auditing conclusions.

[0006] According to an aspect of the present application, a method for specification auditing of energy storage project files is provided. The method comprises:

[0007] Obtaining a target project file to be audited for specification in an energy storage project, and performing file sentence processing on the target project file to obtain a project file sentence;

[0008] For each project file sentence, determining a sentence comprehensive confidence score of the project file sentence according to the project file sentence and pre-determined standard specification clauses;

[0009] In a case where the sub-sentence comprehensive confidence score is less than a preset confidence score threshold, it is determined that the item file sub-sentence does not meet the specification requirement, and in a case where each of the item file sub-sentences meets the specification requirement, it is determined that the target item file meets the specification requirement, wherein the non-compliance with the specification requirement includes specification absence and requirement conflict.

[0010] According to another aspect of the present application, there is provided a device for auditing a specification of an energy storage item file. The device comprises:

[0011] an item file obtaining module, configured to obtain a target item file to be audited for a specification in an energy storage item, and perform file sub-sentence processing on the target item file to obtain item file sub-sentences;

[0012] a confidence score determining module, configured to determine, for each item file sub-sentence, a sub-sentence comprehensive confidence score of the item file sub-sentence according to the item file sub-sentence and each standard specification clause determined in advance;

[0013] a specification requirement auditing module, configured to determine, in a case where the sub-sentence comprehensive confidence score is less than a preset confidence score threshold, that the item file sub-sentence does not meet the specification requirement, and determine, in a case where each of the item file sub-sentences meets the specification requirement, that the target item file meets the specification requirement, wherein the non-compliance with the specification requirement includes specification absence and requirement conflict.

[0014] According to another aspect of the present application, there is provided an electronic device, comprising:

[0015] at least one processor; and

[0016] a memory connected to the at least one processor in communication; wherein

[0017] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for auditing a specification of an energy storage item file according to any one of the embodiments of the present application.

[0018] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the method for auditing a specification of an energy storage item file according to any one of the embodiments of the present application.

[0019] The technical scheme of the embodiment of the present application is as follows: a target project file to be subjected to standard review in an energy storage project is acquired, and the target project file is subjected to file sentence processing to obtain project file sentences; for each project file sentence, a sentence comprehensive confidence score of the project file sentence is determined according to the project file sentence and each standard specification clause determined in advance; in the case that the sentence comprehensive confidence score is less than a preset confidence score threshold, it is determined that the project file sentence does not meet the standard requirement, and in the case that each project file sentence meets the standard requirement, it is determined that the target project file meets the standard requirement, wherein the non-compliance with the standard requirement includes specification absence and requirement conflict, which fundamentally overcomes the drawbacks of low efficiency and easy omission of manual review, improves the approval efficiency, and significantly improves the accuracy and reliability of the review conclusion.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0022] Figure 1 is a flow chart of an energy storage project file standard review method according to an embodiment of the present application;

[0023] Figure 2 is a structural diagram of an energy storage project file standard review device according to an embodiment of the present application;

[0024] Figure 3 is a structural schematic diagram of an electronic device for implementing the energy storage project file standard review method according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0027] Figure 1 A flowchart of a storage energy project file specification auditing method provided for an embodiment of the present application. The embodiment can be applicable to the case of auditing a storage energy project file. The method can be executed by a storage energy project file specification auditing device, which can be realized in the form of hardware and / or software and can be configured in an electronic device. As shown in Figure 1 the method includes:

[0028] S101, obtaining a target project file to be audited in a storage energy project, and performing file sentence processing on the target project file to obtain a project file sentence.

[0029] The target project file is a technical document generated in the whole life cycle of a storage energy project, which needs to be audited in accordance with relevant technical standards and specifications. Its format includes but is not limited to PDF, DOCX, TXT, etc. The target project file can include a system design scheme, an electrical schematic diagram description, a battery cluster specification, a battery management system (BMS) safety policy description, a fire safety design report, a trial operation acceptance scheme, etc.

[0030] Specifically, a corresponding analysis module is called according to the format type of the target project file (such as calling Apache POI library to process DOCX format and using PDFBox library to process PDF format), the text content in the target project file is extracted, and the sentence boundary detection (SBD) algorithm in natural language processing technology is used to intelligently divide the continuous text, so that each project file sentence in the target project file can be obtained.

[0031] S102, for each project file sentence, determining a sentence comprehensive confidence score of the project file sentence according to the project file sentence and each standard specification clause determined in advance.

[0032] wherein the sentence comprehensive confidence score refers to a confidence score for determining whether the project file sentence is consistent with the standard specification clause.

[0033] Specifically, the project file sentence and each of the predetermined standard specification clauses (such as specific clause texts in GB / T 36276, IEC 62933-5-2, UL 9540A) are respectively converted into high-dimensional semantic space vectors, the cosine similarity between each sentence vector and each standard clause vector is determined, and a set of basic semantic similarity scores is obtained. Further, the semantic similarity score is determined as the sentence comprehensive confidence score of the project file sentence.

[0034] It should be noted that the determination of the sentence comprehensive confidence score is not only dependent on a single semantic similarity. The determination of the sentence comprehensive confidence score includes, but is not limited to, keyword matching degree, numerical value and unit compliance, and logical compliance judgment, etc.

[0035] The determination of the sentence comprehensive confidence score of the project file sentence according to the project file sentence and each of the predetermined standard specification clauses includes: performing matching processing according to the project file sentence and each of the predetermined standard specification clauses to determine a sentence matching probability of the project file sentence; performing cosine similarity calculation according to the sentence embedding vector corresponding to the project file sentence and the specification clause vector corresponding to the standard specification clause to determine a sentence similarity score of the project file sentence; and determining the sentence comprehensive confidence score of the project file sentence according to the sentence matching probability and the sentence similarity score.

[0036] wherein the sentence matching probability can refer to the probability value of the matching between the project file sentence and the standard specification clause. The sentence similarity score can refer to the cosine similarity between the sentence embedding vector and the specification clause vector.

[0037] Specifically, the comparison between the project file sentence and the standard specification clause text is to identify the matching degree of key technical terms, mandatory verbs and specific parameters, so as to obtain the sentence matching probability. For example, by constructing a standard term dictionary and a regular expression rule, it is determined whether the core elements specified in the clause are included in the sentence. The sentence matching probability reflects the degree of satisfaction of the project file sentence to the clause. The pre-trained large language model is used to convert the project file sentence and the standard specification clause into vector representations in high-dimensional space respectively, to obtain the sentence embedding vector and the specification clause vector. The cosine similarity between the two vectors is calculated to obtain the sentence similarity score. The sentence similarity score can effectively capture the relevance of the text at the semantic level. The sentence matching probability and the sentence similarity score are summed to determine the sentence comprehensive confidence score of the project file sentence.

[0038] Exemplarily, the matching processing according to the project file sentence and the predetermined respective standard specification clauses to determine the sentence matching probability of the project file sentence comprises: inputting the project file sentence and the standard specification clauses into a pre-constructed target language mapper for matching processing, wherein the target language mapper is a large language model, and the target language mapper is obtained by training according to sample data; and obtaining the sentence matching probability of the project file sentence according to an output of the target language mapper.

[0039] It should be noted that the target language mapper is a large language model that is fine-tuned for a specific purpose. The sample data used for training is composed of manually annotated sample pairs, each of which includes a set of project document sentences and standard specification clauses as input, and an annotated matching probability as expected output. The matching probability is annotated by domain experts according to the degree of compliance of the sentence and the clause (for example, completely compliant is annotated as 1.0, partially compliant is annotated as 0.5, and completely non-compliant is annotated as 0.0). Through supervised learning on this high-quality sample set, the model is trained to learn and internalize the energy field professional knowledge and compliance judgment logic, so that it can simulate experts to perform compliance evaluation.

[0040] Specifically, the project file sentence to be audited and the standard specification clause text are input as a group into the trained target language mapper. Based on the deep understanding of the input text, the model analyzes the consistency of the two in technical requirements and specific measures. The output of the model generates a scalar value between 0 and 1, i.e. the sentence matching probability.

[0041] The target language mapper can understand the deep semantics and intent of technical descriptions. For example, even if the project file sentence and the standard clause are expressed differently, a high matching probability is given based on semantic similarity, thereby significantly improving the accuracy of judgment in fuzzy and irregular expression cases.

[0042] Exemplarily, the determining of the sentence comprehensive confidence score of the project file sentence according to the sentence matching probability and the sentence similarity score comprises: determining a first confidence score according to a pre-set first score weight and the sentence matching probability; determining a second confidence score according to a pre-set second score weight and the sentence similarity score; and determining the sentence comprehensive confidence score of the project file sentence according to the first confidence score and the second confidence score.

[0043] Wherein, the first score weight and the second score weight can be set according to actual conditions. Exemplarily, the first score weight can be 0.6, and the second score weight can be 0.4.

[0044] The product of the first score weight and the sentence matching probability is determined as a first confidence score, and the product of the second score weight and the sentence similarity score is determined as a second confidence score. The score sum of the first confidence score and the second confidence score is determined as a sentence comprehensive confidence score of the project file sentence.

[0045] Exemplarily, the sentence comprehensive confidence score is as follows:

[0046]

[0047] wherein, refers to the sentence comprehensive confidence score, refers to the sentence matching probability, refers to the sentence similarity score, refers to the first score weight, refers to the second score weight.

[0048] S103, in a case where the sentence comprehensive confidence score is less than a preset confidence score threshold, determining that the project file sentence does not meet the standard requirement, and in a case where each of the project file sentences meets the standard requirement, determining that the target project file meets the standard requirement.

[0049] wherein, the non-standard requirement includes a standard absence and a requirement conflict.

[0050] Specifically, the sentence comprehensive confidence score is compared with a preset confidence score threshold constructed in advance, in a case where it is determined that the sentence comprehensive confidence score is less than the preset confidence score threshold, it is determined that the project file sentence does not meet the standard requirement. In a case where it is determined that the sentence comprehensive confidence score is not less than the preset confidence score threshold, it is determined that the project file sentence has met the standard requirement.

[0051] The technical scheme of the embodiment of the application, by acquiring a target project file to be audited in a standard in an energy storage project, and performing file sentence processing on the target project file to obtain a project file sentence; for each project file sentence, according to the project file sentence and each standard specification clause determined in advance, determining a sentence comprehensive confidence score of the project file sentence; in a case where the sentence comprehensive confidence score is less than a preset confidence score threshold, determining that the project file sentence does not meet the standard requirement, and in a case where each of the project file sentences meets the standard requirement, determining that the target project file meets the standard requirement, wherein the non-standard requirement includes a standard absence and a requirement conflict, fundamentally overcoming the drawbacks of low efficiency and easy omission of manual auditing, improving the approval efficiency, and significantly improving the accuracy and reliability of the auditing conclusion.

[0052] Exemplarily, after determining that the project file sentence does not meet the specification requirements, further comprising: determining a target specification clause associated with the project file sentence according to the project file sentence; and generating a rectification suggestion for the project file sentence according to the project file sentence and the target specification clause.

[0053] Specifically, the target specification clause to be rectified according to the current project file sentence is screened out. The project file sentence with compliance defects and its corresponding target specification clause text are input into the fine-tuned large language model. The large language model compares the specific technical requirements of the target specification clause with the current expression of the project file sentence, and identifies the missing technical elements, inaccurate parameter descriptions or ambiguous function definitions. Based on the difference analysis, the large language model directly reconstructs or corrects the expression of the project file sentence based on the target specification clause, and generates a rectification suggestion for the project file sentence.

[0054] Exemplarily, the project file sentence can be "the energy storage system adopts a one-way fuse", the target specification clause can be the double-direction fuse device configured in GB / T 36276 5.3.2, and the rectification suggestion can be: 1) replace with a double-direction fuse; 2) check that the rated current is greater than the discharge peak value; and 3) mark the fuse model in the schematic diagram.

[0055] Exemplarily, after determining that the project file sentence does not meet the specification requirements, further comprising: constructing a case embedding vector corresponding to a demonstration case in a pre-constructed demonstration case library; and determining a target demonstration case corresponding to the project file sentence according to the case embedding vector and a sentence embedding vector of the project file sentence.

[0056] The demonstration case library can store project examples, test reports, and accepted project files, etc., to form demonstration cases. The case embedding vector corresponding to the demonstration case is compared with the sentence embedding vector of the project file sentence, and the demonstration case with the highest similarity is determined as the target demonstration case. The target demonstration case determination process is as follows:

[0057]

[0058] Among them, may refer to the target demonstration case, refers to the sentence embedding vector, refers to the case embedding vector.

[0059] Exemplarily, the technical scheme of the embodiment of the present application can also generate a specification audit report of the target project file, wherein the specification audit report at least includes a rule specification clause, a file modification suggestion and a reference case summary. The specification audit report can be directly used to guide the revision work. The report can be the final output of systematic induction and knowledge expansion of the problems found in the audit.

[0060] Figure 2 A structural schematic diagram of a specification audit device for an energy storage project file provided by the embodiment of the present application is shown in FIG. 1. Figure 2 As shown in the figure, the device comprises:

[0061] A project file acquisition module 201 is configured to acquire a target project file to be audited according to a specification in an energy storage project, and perform file sentence processing on the target project file to obtain a project file sentence.

[0062] A confidence score determination module 202 is configured to determine, for each project file sentence, a sentence comprehensive confidence score of the project file sentence according to the project file sentence and each standard specification clause determined in advance.

[0063] A specification requirement audit module 203 is configured to determine that the project file sentence does not meet the specification requirement in a case where the sentence comprehensive confidence score is less than a preset confidence score threshold, and determine that the target project file meets the specification requirement in a case where each of the project file sentences meets the specification requirement, wherein the non-compliance with the specification requirement includes specification absence and requirement conflict.

[0064] Optionally, the confidence score determination module 202 comprises:

[0065] A matching probability determination unit is configured to determine a sentence matching probability of the project file sentence according to the project file sentence and each standard specification clause determined in advance.

[0066] A similarity score determination unit is configured to determine a sentence similarity score of the project file sentence according to a sentence embedding vector corresponding to the project file sentence and a specification clause vector corresponding to the standard specification clause.

[0067] A confidence score determination unit is configured to determine a sentence comprehensive confidence score of the project file sentence according to the sentence matching probability and the sentence similarity score.

[0068] Optionally, the matching probability determination unit is specifically configured to:

[0069] inputting the project file sentence and the standard specification clause into a pre-constructed target language mapper for matching processing, wherein the target language mapper is a large language model, and the target language mapper is trained according to sample data to obtain;

[0070] According to the output of the target language mapper, the sentence matching probability of the project file sentence is obtained.

[0071] Optionally, a confidence score determination unit, specifically configured to:

[0072] determine a first confidence score according to a pre-set first score weight and the sentence matching probability;

[0073] determine a second confidence score according to a pre-set second score weight and the sentence similarity score;

[0074] determine a comprehensive confidence score of the project file sentence according to the first confidence score and the second confidence score.

[0075] Optionally, the device further comprises a rectification suggestion generation module.

[0076] The rectification suggestion generation module is configured to:

[0077] determine a target specification clause associated with the project file sentence according to the project file sentence after determining that the project file sentence does not meet the specification requirements;

[0078] generate a rectification suggestion for the project file sentence according to the project file sentence and the target specification clause.

[0079] Optionally, the device further comprises a demonstration case determination module.

[0080] The demonstration case determination module is configured to:

[0081] construct a case embedding vector corresponding to the demonstration case according to a demonstration case in a pre-constructed demonstration case library after determining that the project file sentence does not meet the specification requirements;

[0082] determine a target demonstration case corresponding to the project file sentence according to the case embedding vector and a sentence embedding vector of the project file sentence.

[0083] Optionally, the device further comprises an audit report generation module.

[0084] The audit report generation module is configured to:

[0085] A specification audit report of the target project file is generated, wherein the specification audit report at least includes a non-compliant specification clause, a file modification suggestion, and a reference case abstract.

[0086] The technical scheme of the embodiment of the present application, by obtaining a target project file to be audited in a storage energy project, and performing file sentence processing on the target project file, obtaining a project file sentence; for each project file sentence, determining a sentence comprehensive confidence score of the project file sentence according to the project file sentence and each standard specification clause determined in advance; in the case that the sentence comprehensive confidence score is less than a preset confidence score threshold, determining that the project file sentence does not meet the specification requirements, and in the case that each of the project file sentences meets the specification requirements, determining that the target project file meets the specification requirements, wherein the non-compliance with the specification requirements includes specification missing and requirement conflict, fundamentally overcoming the drawbacks of low efficiency and easy omission of manual auditing, improving the approval efficiency, and significantly improving the accuracy and reliability of the audit conclusion.

[0087] The storage energy project file specification auditing device provided in the embodiment of the present application can execute the storage energy project file specification auditing method provided in any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0088] Figure 3 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0089] As Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0090] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0091] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the energy storage project file specification auditing method.

[0092] In some embodiments, the energy storage project file specification auditing method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the energy storage project file specification auditing method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the energy storage project file specification auditing method by any other appropriate means, such as by means of firmware.

[0093] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0094] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0095] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0096] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0097] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0098] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0099] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0100] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for reviewing the specifications of energy storage project documents, characterized in that, include: Obtain the target project documents that are to be subject to regulatory review in the energy storage project, and perform document segmentation on the target project documents to obtain project document segments; For each project document clause, a clause composite confidence score is determined based on the project document clause and pre-determined standard specification clauses. If the overall confidence score of the clause is less than a preset confidence score threshold, the clause of the project document is determined to be non-compliant with the specification requirements. If each clause of the project document is compliant with the specification requirements, the target project document is determined to be compliant with the specification requirements. The non-compliance with the specification requirements includes missing specifications and contradictory requirements.

2. The method according to claim 1, characterized in that, The determination of the comprehensive confidence score of the project document clauses based on the project document clauses and the pre-determined standard specification clauses includes: The matching probability of the project document sentences is determined by performing matching processing based on the pre-determined standard and specification clauses. Based on the sentence embedding vectors corresponding to the project document sentences and the standard clause vectors corresponding to the standard clauses, cosine similarity is calculated to determine the sentence similarity score of the project document sentences. Based on the sentence matching probability and the sentence similarity score, the overall sentence confidence score of the project file sentence is determined.

3. The method according to claim 2, characterized in that, The step of matching the project document sentences with pre-determined standard specification clauses to determine the sentence matching probability of the project document sentences includes: The project file sentences and the standard specification clauses are input into a pre-built target language mapper for matching processing. The target language mapper is a large language model, which is trained based on sample data. Based on the output of the target language mapper, the sentence matching probability of the project file sentences is obtained.

4. The method according to claim 2, characterized in that, The step of determining the overall confidence score of the project document sentences based on the sentence matching probability and the sentence similarity score includes: The first confidence score is determined based on the pre-set first score weight and the sentence matching probability; The second confidence score is determined based on the pre-set second score weight and the clause similarity score; The combined confidence score of the clause in the project document is determined based on the first confidence score and the second confidence score.

5. The method according to claim 1, characterized in that, After determining that the project document clauses do not meet the specifications, the following steps are also included: Based on the project document clauses, determine the target specification clauses associated with the project document clauses; Based on the project document clauses and the target specification clauses, generate rectification suggestions for the project document clauses.

6. The method according to claim 1, characterized in that, After determining that the project document clauses do not meet the specifications, the following steps are also included: Based on the demonstration cases in the pre-built demonstration case library, construct the case embedding vector corresponding to the demonstration cases; Based on the case embedding vector and the sentence embedding vector of the project file sentence, the target demonstration case corresponding to the project file sentence is determined.

7. The method according to claim 1, characterized in that, The method further includes: Generate a specification review report for the target project documents, wherein the specification review report includes at least the non-compliant specification clauses, document modification suggestions, and a summary of reference cases.

8. A device for reviewing the specifications of energy storage project documents, characterized in that, include: The project document acquisition module is used to acquire the target project documents that need to be reviewed for specifications in the energy storage project, and to process the target project documents into sentence segments to obtain project document segments. The confidence score determination module is used to determine the overall confidence score of each project document sentence based on the project document sentence and pre-determined standard specification clauses. The specification review module is used to determine that a clause in a project document does not meet the specification requirements if the overall confidence score of the clause is less than a preset confidence score threshold, and to determine that the target project document meets the specification requirements if every clause in the project document meets the specification requirements. The non-compliance with the specification requirements includes missing specifications and contradictory requirements.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the energy storage project document specification review method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the energy storage project document specification review method according to any one of claims 1-7.

Images