Contract label extraction method and device, equipment, medium and program product

Abstract

The invention discloses a contract label extraction method, device and equipment, a medium and a product. The method comprises the following steps: acquiring an unformatted text in a contract text as a to-be-processed text; based on a pre-trained word extraction model, performing language processing on the to-be-processed text to obtain a candidate word set; and determining a label matched with the contract text according to a matching result of each candidate word in the candidate word set and each reference word in a pre-acquired corpus. According to the technical scheme, the problems of low tag extraction efficiency, poor accuracy and the like in the process that the partner accesses the open bank are solved, the candidate words are automatically extracted from the contract signed by the bank and the partner based on the word extraction model, and the tag extraction efficiency and accuracy are improved by performing standardized matching on the candidate words.

Description

Technical Field

[0001] The present invention relates to the technical field of text processing, and in particular to a contract label extraction method, device, equipment, medium and product. Background Art

[0002] Open banking mainly empowers partners with their own capabilities, and partners provide financial services to the C-end through their own scenario output channels to achieve data sharing and user growth. As an important means of bank-side operation, the open banking operation management platform is responsible for partner access, bank service resource management and scenario data analysis. Business personnel need to formulate personalized business processes for different cooperation scenarios in a timely and effective manner to shorten the cycle of partners accessing open banking.

[0003] At present, business process control is mainly carried out by business personnel on the management platform. They formulate corresponding processes based on the selected scenarios and access platform labels. The scenarios and access technology labels are selected manually, which may lead to inaccurate label recognition, missed selections, and wrong label selections, resulting in fewer or more processes, extending the approval time, and failing to meet the needs of quickly formulating partner access processes. Summary of the invention

[0004] The present invention provides a contract label extraction method, device, equipment, medium and product to solve the problems of low efficiency and poor accuracy of label extraction during the process of partners accessing open banks. Based on the word extraction model, candidate words are automatically extracted from the contract signed between the bank and the partners. By performing standardized matching on the candidate words, the efficiency and accuracy of label extraction are improved.

[0005] According to one aspect of the present invention, a contract tag extraction method is provided, the method comprising:

[0006] Obtain the non-formatted text in the contract text as the text to be processed;

[0007] Based on the pre-trained word extraction model, language processing is performed on the text to be processed to obtain a set of candidate words;

[0008] According to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus, a label matching the contract text is determined.

[0009] According to another aspect of the present invention, a contract label extraction device is provided, the device comprising:

[0010] A text acquisition module is used to acquire non-formatted text in the contract text as text to be processed;

[0011] A candidate word generation module is used to perform language processing on the text to be processed based on a pre-trained word extraction model to obtain a candidate word set;

[0012] The contract label determination module is used to determine the label matching the contract text according to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus.

[0013] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0014] At least one processor; and a memory communicatively connected to the at least one processor; wherein 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 so that the at least one processor can execute the contract label extraction method described in any embodiment of the present invention.

[0015] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the contract label extraction method described in any embodiment of the present invention when executed.

[0016] According to another aspect of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the contract tag extraction method according to any embodiment of the present invention is implemented.

[0017] The technical solution of the embodiment of the present invention obtains the non-formatted text in the contract text as the text to be processed; performs language processing on the text to be processed based on a pre-trained word extraction model to obtain a candidate word set; and determines the label matching the contract text according to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus. This technical solution solves the problems of low efficiency and poor accuracy of label extraction during the process of partners accessing open banks. Based on the word extraction model, candidate words are automatically extracted from the contract signed between the bank and the partner, and the efficiency and accuracy of label extraction are improved by performing standardized matching on the candidate words.

[0018] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 is a flow chart of a contract tag extraction method provided according to Embodiment 1 of the present invention;

[0021] Figure 2 is a flow chart of a contract tag extraction method provided according to Embodiment 2 of the present invention;

[0022] Figure 3 is a structural schematic diagram of a contract label extraction device provided according to Embodiment 3 of the present invention;

[0023] Figure 4 It is a structural schematic diagram of an electronic device for implementing the contract tag extraction method of an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0026] Embodiment 1

[0027] Figure 1A flowchart of a contract tag extraction method is provided for the first embodiment of the present invention. This embodiment can be applied to the scenario of a partner accessing an open bank, especially the identification of the partner's access scenario. The method can be executed by a contract tag extraction device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0028] S110. Obtain unformatted text in the contract text as text to be processed.

[0029] This solution can be executed by electronic devices such as computers and servers. The electronic devices can obtain the contract text signed between the partner and the bank and identify the unformatted text in the contract text. The unformatted text can be the unformatted clauses in the contract text. The electronic device can use the unformatted text in the contract text as the text to be processed.

[0030] S120: Based on the pre-trained word extraction model, perform language processing on the text to be processed to obtain a candidate word set.

[0031] The electronic device can pre-train a word extraction model based on natural language processing technology to perform language processing such as word segmentation, part-of-speech recognition, and word segmentation removal on the text to be processed to obtain a candidate word set. It is understandable that the candidate word set may include multiple candidate words, and the candidate words may be words extracted from the text to be processed that can represent the access scenario information of the partner.

[0032] Optionally, the word extraction model is a bidirectional long short-term memory model based on conditional random fields;

[0033] The word extraction model is trained based on a pre-acquired contract sample data set; the contract sample data set includes multiple groups of sample data, each group of sample data includes a contract text and a label matching the contract text;

[0034] The tagging method of the contract text matching label is: the sequence tagging weight of the sentence start position is less than the sequence tagging weight of the sentence middle position, and the sequence tagging weight of the sentence start position is less than the sequence tagging weight of the sentence end position.

[0035] The LSTM-CRF model is a sequence labeling model that combines LSTM (Long Short-Term Memory) and CRF (Conditional Random Field), which can be used for natural language processing tasks. LSTM can extract features from text sequences and model the context of text sequences, while CRF can model the constraint relationship between tags to improve the overall performance of the LSTM-CRF model.

[0036] In the LSTM-CRF model, LSTM acts as a feature extractor to extract features of the input text sequence, and CRF uses the extracted features of the text sequence to predict labels. CRF models the dependency between labels by defining emission scores and transition probabilities. The emission score represents the probability of each label on a given input data, and the transition probability represents the probability of transferring from one label to another.

[0037] It is easy to understand that the annotation weight of the text sequence refers to the different importance or priority given to different parts of the text sequence during the text annotation process, so as to reflect the importance of each part to the overall understanding and analysis of the text. According to the characteristics of the contract label, the sequence annotation weights at the mid-sentence position and the end-of-sentence position are set to be greater than the sequence annotation weight at the beginning of the sentence, so that the word extraction model can effectively overcome the problem of inaccurate label extraction caused by inaccurate feature settings during the training process.

[0038] In this solution, the word extraction model includes a word segmentation unit, a part-of-speech tagging unit, a word vector calculation unit, and a stop word removal unit;

[0039] The pre-trained word extraction model is used to perform language processing on the text to be processed to obtain a candidate word set, including:

[0040] Segment the text to be processed based on the segmentation unit to obtain multiple segmentations, and mark the part of speech of each segmentation based on the part of speech tagging unit;

[0041] Based on the stop word removal unit, the stop words in each participle are removed according to the part of speech of each participle, and based on the word vector calculation unit, the word vector matching each participle is generated to obtain a candidate word set.

[0042] After the training is completed, the electronic device can segment the text to be processed based on the segmentation unit to obtain multiple segmentations, and mark the part of speech of each segmentation based on the part of speech tagging unit. After determining the part of speech of each segmentation, based on the stop word removal unit, the electronic device can remove the stop words in each segmentation according to the part of speech of each segmentation, leaving the segmentations with actual meanings such as verbs, nouns and adjectives. After removing the stop words, the remaining segmentations can be used as candidate words to form a candidate word set. Based on the word vector calculation unit, the electronic device can generate word vectors that match each segmentation to obtain a candidate word set. It can be understood that the word vector can represent the segmentation in the form of quantity to facilitate comparison and calculation between words.

[0043] S130: Determine a label that matches the contract text according to a matching result between each candidate word in the candidate word set and each reference word in the pre-acquired corpus.

[0044] The electronic device can pre-build a corpus to store professional vocabulary involved in the partner access scenario. The electronic device can use the professional vocabulary in the corpus as a reference word to compare with the candidate words in the candidate word set, determine whether the candidate words match the reference words, and then determine the label corresponding to the contract text based on the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus. Specifically, judging whether the candidate word matches the reference word can be comparing whether the two are identical, similar or synonymous. The labels matched by the contract text can be used to represent the keywords for the partner to access the open bank. The open bank can formulate a partner access process based on the labels matched by the contract text.

[0045] In a feasible solution, determining the label matching the contract text according to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus includes:

[0046] Taking each candidate word in the candidate word set as a target word in turn, and calculating the similarity between the target word and each reference word in the pre-acquired corpus;

[0047] According to the similarity between the target word and each reference word, the matching result of the target word is determined;

[0048] If the target word has a matching reference word, the reference word is used as a label for contract text matching.

[0049] The electronic device may sequentially use each candidate word in the candidate word set as a target word, and sequentially calculate the similarity between the target word and each reference word in the corpus. Specifically, the reference word may be represented in the form of a vector, and the electronic device may determine the similarity between the candidate word and the reference word by calculating the distance between the word vector of the candidate word and the word vector of the reference word. The distance may be a Euclidean distance, a cosine distance, etc. The electronic device may determine the matching result of the target word based on the similarity between the target word and each reference word.

[0050] For example, the similarity between the target word and each reference word is compared with a preset similarity threshold. If there is a reference word whose similarity with the target word is higher than the similarity threshold, the similarity between the target word and each reference word is sorted, and the reference word with the highest similarity is used as the reference word matching the target word. If there is no reference word whose similarity with the target word is higher than the similarity threshold, it is determined that there is no matching reference word for the target word. If there is a matching reference word for the target word, the reference word matching the target word is used as the label for the contract text matching.

[0051] The technical solution of the embodiment of the present invention obtains the non-formatted text in the contract text as the text to be processed; performs language processing on the text to be processed based on a pre-trained word extraction model to obtain a candidate word set; and determines the label matching the contract text according to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus. This technical solution solves the problems of low efficiency and poor accuracy of label extraction during the process of partners accessing open banks. Based on the word extraction model, candidate words are automatically extracted from the contract signed between the bank and the partner, and the efficiency and accuracy of label extraction are improved by performing standardized matching on the candidate words.

[0052] Embodiment 2

[0053] Figure 2 This is a flow chart of a contract tag extraction method provided in the second embodiment of the present invention. This embodiment is based on the above embodiment and is refined. Figure 2 As shown, the method includes:

[0054] S210. Obtain unformatted text in the contract text as text to be processed.

[0055] S220: Based on the pre-trained word extraction model, perform language processing on the text to be processed to obtain a set of candidate words.

[0056] S230 , taking each candidate word in the candidate word set as a target word in turn, and calculating the similarity between the target word and each reference word in the pre-acquired corpus.

[0057] S240: Determine a matching result of the target word according to the similarity between the target word and each reference word.

[0058] S250: If the target word has a matching reference word, use the reference word as a label for matching the contract text.

[0059] In this solution, if there is no matching reference word for the target word, the electronic device can obtain the explanatory text of the target word through the retrieval platform, match the explanatory text of the target word with the reference words in the corpus, and determine the label that matches the contract text based on the matching results between the explanatory text of the target word and each reference word.

[0060] If there is no matching reference word for the target word, the electronic device may also send the target word to the service end, and the service personnel may manually recognize the target word. The electronic device may determine the matching label of the cooperative text according to the recognition result of the target word fed back by the service end.

[0061] S260: If the target word has a matching reference word, determine a target word group that matches the reference word, and determine in turn whether the target word is identical to each synonym in the target word group.

[0062] In a preferred solution, the corpus includes a plurality of word groups, each word group includes a plurality of synonyms, and each word group corresponds to a reference word; the reference word is determined based on the cluster center of each synonym in the word group.

[0063] The electronic device can pre-group synonyms in the corpus, calculate the cluster center of the word group based on the word vectors of each synonym, and use the synonym closest to the cluster center as the reference word of the word group to represent the semantic features of the entire word group.

[0064] If the target word has a matching reference word, the electronic device can determine the target word group that the reference word matches, and determine whether the target word is the same as each synonym in the target word group. If there is a synonym in the target word group that is the same as the target word, it means that the target word is not a "new word". If there is no synonym in the target word group that is the same as the target word, it means that the target word is a "new word" in the word group.

[0065] S270: If there is no synonym identical to the target word in the target word group, add the target word to the target word group.

[0066] The electronic device may add the target word to the word group, and recalculate the cluster center of the word group, thereby updating the reference word of the word group.

[0067] This solution can synchronously add "new words" to the corpus during the contract tag extraction process, so that the corpus is continuously updated and the reliability and accuracy of contract tag extraction are improved.

[0068] The technical solution of the embodiment of the present invention obtains the non-formatted text in the contract text as the text to be processed; performs language processing on the text to be processed based on a pre-trained word extraction model to obtain a candidate word set; and determines the label matching the contract text according to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus. This technical solution solves the problems of low efficiency and poor accuracy of label extraction during the process of partners accessing open banks. Based on the word extraction model, candidate words are automatically extracted from the contract signed between the bank and the partner, and the efficiency and accuracy of label extraction are improved by performing standardized matching on the candidate words.

[0069] Embodiment 3

[0070] Figure 3 This is a schematic diagram of the structure of a contract label extraction device provided in Embodiment 3 of the present invention.

[0071] like Figure 3 As shown, the device comprises:

[0072] A text acquisition module 310 is used to acquire non-formatted text in the contract text as text to be processed;

[0073] A candidate word generation module 320 is used to perform language processing on the text to be processed based on a pre-trained word extraction model to obtain a candidate word set;

[0074] The contract label determination module 330 is used to determine the label matching the contract text according to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus.

[0075] In this solution, optionally, the word extraction model includes a word segmentation unit, a part-of-speech tagging unit, a word vector calculation unit, and a stop word removal unit;

[0076] The candidate word generation module 320 is specifically used for:

[0077] Segment the text to be processed based on the segmentation unit to obtain multiple segmentations, and mark the part of speech of each segmentation based on the part of speech tagging unit;

[0078] Based on the stop word removal unit, the stop words in each participle are removed according to the part of speech of each participle, and based on the word vector calculation unit, the word vector matching each participle is generated to obtain a candidate word set.

[0079] In a feasible solution, the contract tag determination module 330 is specifically used to:

[0080] Taking each candidate word in the candidate word set as a target word in turn, and calculating the similarity between the target word and each reference word in the pre-acquired corpus;

[0081] According to the similarity between the target word and each reference word, the matching result of the target word is determined;

[0082] If the target word has a matching reference word, the reference word is used as a label for contract text matching.

[0083] In a preferred solution, the corpus includes a plurality of word groups, each word group includes a plurality of synonyms, and each word group corresponds to a reference word; the reference word is determined based on the cluster center of each synonym in the word group.

[0084] Based on the above solution, the device further includes a word group supplement module, which is used to:

[0085] After determining the matching result of the target word according to the similarity between the target word and each reference word, if the target word has a matching reference word, then determining the target word group that the reference word matches, and determining in turn whether the target word is the same as each synonym in the target word group;

[0086] If there is no synonym identical to the target word in the target word group, the target word is added to the target word group.

[0087] In this embodiment, optionally, the word extraction model is a bidirectional long short-term memory model based on conditional random fields;

[0088] The word extraction model is trained based on a pre-acquired contract sample data set; the contract sample data set includes multiple groups of sample data, each group of sample data includes a contract text and a label matching the contract text;

[0089] The tagging method of the contract text matching label is: the sequence tagging weight of the sentence start position is less than the sequence tagging weight of the sentence middle position, and the sequence tagging weight of the sentence start position is less than the sequence tagging weight of the sentence end position.

[0090] The contract label extraction device provided in the embodiment of the present invention can execute the contract label extraction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0091] Embodiment 4

[0092] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0093] like Figure 4As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0094] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0095] The processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special 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 411 executes the various methods and processes described above, such as the contract tag extraction method.

[0096] In some embodiments, the contract tag extraction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the contract tag extraction method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to execute the contract tag extraction method in any other appropriate manner (e.g., by means of firmware).

[0097] Various implementations 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), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0098] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer or other programmable contract label extraction device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0099] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0100] To provide interaction with a user, the systems and techniques described herein may 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0101] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0102] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0103] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0104] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A contract tag extraction method, characterized in that: The method comprises: Obtain the non-formatted text in the contract text as the text to be processed; Based on the pre-trained word extraction model, language processing is performed on the text to be processed to obtain a set of candidate words; According to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus, a label matching the contract text is determined.

2. The method according to claim 1, characterized in that The word extraction model includes a word segmentation unit, a part-of-speech tagging unit, a word vector calculation unit and a stop word removal unit; The pre-trained word extraction model is used to perform language processing on the text to be processed to obtain a candidate word set, including: Segment the text to be processed based on the segmentation unit to obtain multiple segmentations, and mark the part of speech of each segmentation based on the part of speech tagging unit; Based on the stop word removal unit, the stop words in each participle are removed according to the part of speech of each participle, and based on the word vector calculation unit, the word vector matching each participle is generated to obtain a candidate word set.

3. The method according to claim 1, characterized in that The step of determining a label matching the contract text according to a matching result between each candidate word in the candidate word set and each reference word in the pre-acquired corpus includes: Taking each candidate word in the candidate word set as a target word in turn, and calculating the similarity between the target word and each reference word in the pre-acquired corpus; According to the similarity between the target word and each reference word, the matching result of the target word is determined; If the target word has a matching reference word, the reference word is used as a label for contract text matching.

4. The method according to claim 1, characterized in that: The corpus includes a plurality of word groups, each word group includes a plurality of synonyms, and each word group corresponds to a reference word; the reference word is determined according to the cluster center of each synonym in the word group.

5. The method according to claim 4, characterized in that After determining the matching result of the target word according to the similarity between the target word and each reference word, the method further includes: If the target word has a matching reference word, determining a target word group that the reference word matches, and determining in turn whether the target word is identical to each synonym in the target word group; If there is no synonym identical to the target word in the target word group, the target word is added to the target word group.

6. The method according to claim 2, characterized in that The word extraction model is a bidirectional long short-term memory model based on conditional random fields; The word extraction model is trained based on a pre-acquired contract sample data set; the contract sample data set includes multiple groups of sample data, each group of sample data includes a contract text and a label matching the contract text; The tagging method of the contract text matching label is: the sequence tagging weight of the sentence start position is less than the sequence tagging weight of the sentence middle position, and the sequence tagging weight of the sentence start position is less than the sequence tagging weight of the sentence end position.

7. A contract label extraction device, characterized in that: The device comprises: A text acquisition module is used to acquire non-formatted text in the contract text as text to be processed; A candidate word generation module is used to perform language processing on the text to be processed based on a pre-trained word extraction model to obtain a candidate word set; The contract label determination module is used to determine the label matching the contract text according to the matching results of each candidate word in the candidate word set and each reference word in the pre-acquired corpus.

8. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the contract tag extraction method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the contract tag extraction method according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the contract tag extraction method according to any one of claims 1 to 6 is implemented.

Images