Contract template searching method and device, equipment and storable medium

Abstract

The invention provides a contract template searching method and device, computer equipment and a computer readable storage medium, and belongs to the field of financial science and technology. The contract template search method comprises the following steps: in response to a template search instruction triggered by a contract management interface, dividing a key field data set based on importance indication information of each field in key field data to obtain a primary field subset and an auxiliary field subset of the template search instruction; performing matching processing on the basis of the primary field subset and a key field of each contract template in a preset contract template database to obtain a primary selection template set matched with the primary field subset; performing matching processing on the basis of the description features of the auxiliary field subset and the description features of each contract template in the primary selection template set to obtain a re-selection template set matched with the auxiliary field subset; and obtaining the target contract template from the re-selected template set. According to the method, the search efficiency and the search accuracy of the contract template can be improved.

Description

Technical Field

[0001] The present application relates to the field of data management technology, and in particular to a contract template search method, device, computer equipment and computer-readable storage medium. Background Art

[0002] With the continuous development of computer technology, the management of various types of information data (such as contracts) is gradually moving towards digitalization. For example, in insurance business scenarios, a large amount of contract management is usually required. Due to changes in business scenarios, the contract templates required for many products launched by enterprises may be different, resulting in a large number of electronic contract templates. When making a new electronic contract, it is usually necessary to search for a contract template that matches the current needs from a large number of electronic contract template databases; in related technologies, the target contract template is mainly searched out by searching and matching key fields. However, the inventor of this application found in the actual research and development process that due to the large amount of contract template data in the contract template database, the contract template searched out in this way has a low degree of matching with the contract template currently required. Summary of the invention

[0003] The present application provides a contract template search method, device, computer equipment and computer-readable storage medium, which can improve the search efficiency and search accuracy of contract templates, and improve the matching degree between the search results of contract templates and the actual required contract templates.

[0004] In a first aspect, the present application provides a contract template search method, comprising:

[0005] In response to a template search instruction triggered by a contract management interface, obtaining a key field data set of the template search instruction and importance indication information of each field in the key field data;

[0006] Based on the importance indication information of each field, the key field data set is divided to obtain a primary field subset and an auxiliary field subset of the template search instruction;

[0007] Based on the primary field subset, matching processing is performed with key fields of each contract template in a preset contract template database to obtain a set of preliminary selected templates matching the primary field subset;

[0008] Based on the description features of the auxiliary field subset and the description features of each contract template in the primary selected template set, a matching process is performed to obtain a secondary selected template set matching the auxiliary field subset;

[0009] Obtain a target contract template from the reselected template set.

[0010] In a second aspect, the present application provides a contract template search device, comprising:

[0011] A response module, configured to respond to a template search instruction triggered by a contract management interface, and obtain a key field data set of the template search instruction and importance indication information of each field in the key field data;

[0012] A partitioning module, configured to partition the key field data set based on the importance indication information of each field to obtain a primary field subset and an auxiliary field subset of the template search instruction;

[0013] A search module, configured to perform matching processing based on the primary field subset with key fields of each contract template in a preset contract template database, and obtain a set of preliminary selected templates matching the primary field subset;

[0014] The search module is further used to perform matching processing based on the description features of the auxiliary field subset and the description features of each contract template in the primary selected template set, so as to obtain a secondary selected template set matching the auxiliary field subset;

[0015] The search module is also used to obtain a target contract template from the reselected template set.

[0016] In a third aspect, the present application also provides a computer device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the contract template search method when executing the computer program.

[0017] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is loaded by a processor to execute the contract template search method.

[0018] In the present application, the key field data set is divided by importance indication information to obtain the primary field subset and the auxiliary field subset of the template search instruction, and the primary field subset and the auxiliary field subset are used in turn to search for the target contract template. On the one hand, since the key field matching method needs to traverse all electronic contract templates and match them with the key fields respectively, by using the primary field subset, the template retrieval process can pay more attention to the search template for a part of information with relatively high importance in the key field data set, reducing the problem of matching key fields with relatively low importance one by one, thereby avoiding the problem of low search efficiency caused by matching key fields; on the other hand, since some key fields of the contract template may not have associated records or the field values ​​are not completely matched, matching all key fields of the key field data set may cause some contract templates to be missed in the search. In the search, the key field matching method is used to first search for the preliminary template set that matches the primary field subset. Since the key fields with relatively high importance will be searched using the key field matching method, it can be ensured that the contract templates that match the user's needs can be accurately screened out first, thereby narrowing the retrieval scope of the contract template for the subsequent search process; then the description feature matching method is used to search for the secondary template set that matches the auxiliary field subset. Since the key fields with relatively low importance will be unified into a description feature for matching, there is no need to traverse the text information of all contract templates in the database. The contract template with the highest matching degree with all fields of the auxiliary field subset can be further screened out, effectively avoiding the problem of missed search of contract templates. Therefore, the search efficiency and search accuracy of the contract template can be improved, and the matching degree between the search results of the contract template and the actual demand contract template can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a flow chart of a contract template search method provided in an embodiment of the present application;

[0021] Figure 2 is a schematic diagram illustrating a contract management interface including a field input area provided in an embodiment of the present application;

[0022] Figure 3 It is a schematic diagram illustrating a contract management interface including a selection control of multiple field types provided in an embodiment of the present application;

[0023] Figure 4It is a schematic diagram of the structure of an embodiment of a contract template search device provided in an embodiment of the present application;

[0024] Figure 5 It is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0027] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0028] In order to enable any person skilled in the art to implement and use the present application, the following description is provided. In the following description, details are listed for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present application can also be implemented without using these specific details. In other examples, the known process will not be elaborated in detail to avoid unnecessary details that make the description of the present application embodiment obscure. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest range of principles and features disclosed in accordance with the embodiments of the present application.

[0029] Embodiments of the present application provide a contract template search method, apparatus, computer device, and computer-readable storage medium.

[0030] The executor of the contract template search method in the embodiment of the present application may be the contract template search device provided in the embodiment of the present application, or the computer device provided in the embodiment of the present application, wherein the contract template search device may be implemented in hardware or software.

[0031] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0032] See also Figure 1 , Figure 1 1 is a flow chart of a contract template search method provided in an embodiment of the present application. The contract template search method includes steps 101 to 105, wherein:

[0033] 101. In response to a template search instruction triggered by a contract management interface, obtain a key field data set of the template search instruction and importance indication information of each field in the key field data.

[0034] The contract management interface is a visual interface of the contract template management platform. Through the visual contract template management platform, users can access the platform across platforms and can transmit the storage information, generation information, and other information of the electronic contract or electronic contract template to other interfaces for sharing and interaction. For example, the contract management interface provided by the contract template management platform can realize the following functions:

[0035] 1) Create contract templates: First, create contract templates of different types and purposes based on the business needs and regulatory requirements of the enterprise by visually integrating template management backend or operation and maintenance operations. These templates can be modified and customized according to specific circumstances.

[0036] 2) Store contract templates: Store the created contract templates in the database for subsequent use. The template storage here needs to define the key information of the contract, and define the online key information fields of the contract in sufficient detail, including the type, length, enumeration value, business meaning and other information of the template information, so as to facilitate the verification and entry of the contract. The contract template needs to provide a visual customization interface for template definition business personnel to adjust and define the template.

[0037] 3) Retrieve contract template: According to the parameters entered by the user, the corresponding contract template is retrieved from the database by searching keywords or matching rules.

[0038] 4) Generate a contract: According to the retrieved contract template, automatically generate the corresponding contract text or enter the contract according to the requirements of the contract template. The user can make necessary modifications and additions to the generated contract within the scope of the template. When the contract is generated, the contract information is broadcast to all management systems to provide integrated query information.

[0039] 5) Store and manage contracts: Store the generated contracts in the database and classify, archive and manage them. At the same time, you can set the version control and approval process of the contract. The stored contracts give other integrated systems the ability to query and change based on the generated contract number.

[0040] 6) Statistical analysis: Through statistical analysis of contract data, we can understand the business status and trends of the enterprise and provide data support for decision-making.

[0041] Therefore, through the contract management interface provided by the contract template management platform, contracts can be automatically and standardizedly generated and managed, improving work efficiency and accuracy; at the same time, through statistical analysis of contract data, the business status and trends of the enterprise can be better understood, providing data support for decision-making. In addition, the contract template management platform can also be integrated with other systems of the enterprise to achieve information sharing and interaction. It can save a lot of manpower and time resources for contract management; improve the efficiency of contract review; reduce contract risks; and provide a more convenient way of working for contract managers.

[0042] Among them, key fields may include target business information, applicable region information, and target version information. The target business information indicates the business type, product type, information of the parties involved in the transaction, etc. required for the template search instruction. The applicable region information indicates the specific geographical area to which the template required for the template search instruction is applicable. The target version information indicates the version type required for the template search instruction, including generation time, iterative version, degree of newness, etc.

[0043] The key field data set includes multiple key fields selected or input by the user.

[0044] In step 101, there are multiple ways to obtain the key field data set, illustratively including:

[0045] (1) In some embodiments, Figure 2 As shown, the contract management interface may include a field input area, and the user can enter key fields in the field input area and click the "search" control to trigger the template search instruction. As a result, the key fields entered by the user in the field input area can be obtained as the key field data set of the template search instruction.

[0046] (2) In some embodiments, Figure 2As shown, the contract management interface may include selection controls for multiple field types. First, the user can click on a selection control for field type i. At this time, the contract management interface will display all field values ​​of field type i (such as the field type can be an applicable area) (such as City A, City B, City C...) as selected key fields in the form of a drop-down menu option in the selection control for field type i; then, the user can select a field value that matches the current requirement from all field values ​​of field type i displayed in the form of a drop-down menu option, as the key field, and click the "Search" control to trigger the template search instruction, thereby obtaining the key field selected by the user from the drop-down menu option as the key field data set for the template search instruction.

[0047] 102. Based on the importance indication information of each field, divide the key field data set to obtain a primary field subset and an auxiliary field subset of the template search instruction.

[0048] There are many ways to implement step 102, illustratively including:

[0049] (1) The importance indication information is the field selection order. For example, the key field data set can be divided according to a preset proportion (such as 40% for primary fields and 60% for auxiliary fields) according to the field selection order of each field, and the fields with a higher priority as the primary fields in the selection order are divided to obtain the primary field subset and the auxiliary field subset of the template search instruction.

[0050] (2) The importance indication information is a preset field priority. For example, the key field data set can be divided according to the preset proportion (such as 40% for primary field and 60% for auxiliary field) according to the preset field priority of each field, and the higher the preset field priority, the higher the priority of the primary field, to obtain the primary field subset and the auxiliary field subset of the template search instruction.

[0051] (3) The importance indication information includes a field selection order and a preset field priority. Exemplarily, based on the field selection order of each field and the preset field priority of each field, the classification importance of each field is determined; based on the classification importance of each field, each field is regarded as a primary class field or an auxiliary class field, wherein the importance of the primary class field is greater than the importance of the primary class field; the set of the primary class fields is regarded as the primary field subset, and the set of the auxiliary class fields is regarded as the auxiliary field subset.

[0052] 103. Matching is performed based on the primary field subset and key fields of each contract template in a preset contract template database to obtain a set of preliminary templates matching the primary field subset.

[0053] Exemplarily, for each contract template k in the preset contract template database, the following process is performed: first, a field check is performed on the storage document of the contract template k through a string matching algorithm to determine whether the contract template k contains any key field in the primary field subset, and the similarity between the storage document of the contract template k and each key field in the primary field subset is compared using a vector space model. If the similarity between the storage document of the contract template k and all key fields in the primary field subset is greater than a preset similarity threshold, the contract template k is added to the set of preliminary templates that match the primary field subset. By analogy, it can be determined whether each contract template in the preset contract template database is added to the set of preliminary templates. When all contract templates in the preset contract template database are traversed, a set of preliminary templates that match the primary field subset is obtained.

[0054] 104. Matching processing is performed based on the description features of the auxiliary field subset and the description features of each contract template in the primary selected template set to obtain a secondary selected template set that matches the auxiliary field subset.

[0055] The target description feature refers to the description feature of the auxiliary field subset.

[0056] There are many specific implementations of step 104, which include, for example:

[0057] (1) In some embodiments, a matching method of the degree of matching between features can be used to select the top N contract templates in the matching degree between the corresponding description features and the target description features from the preliminary template set as the reselected template set. In this case, step 104 can specifically include the following steps: using a preset feature extractor, performing description processing based on the auxiliary field subset to obtain the target description features of the auxiliary field subset; using the preset feature extractor, performing description processing on each contract template in the preliminary template set to obtain the description features of each contract template in the preliminary template set; obtaining the top N contract templates in the matching degree between the description features and the target description features from the preliminary template set, and adding them to the reselected template set.

[0058] (2) In some embodiments, a feature clustering method may be used to select contract templates whose corresponding description features are closer to the target description features from the initial template set as the reselected template set. In this case, step 104 may specifically include the following steps 1041 to 1044:

[0059] 1041. Perform description processing based on the auxiliary field subset through a preset feature extractor to obtain target description features of the auxiliary field subset.

[0060] Exemplarily, the preset feature extractor can be a recurrent neural network (RNN), a convolutional neural network (CNN), a transformer, etc., which is not limited here. Specifically, first, each key field in the auxiliary field subset is characterized by a feature vector to obtain a feature vector of each key field; then, the feature vectors of all key fields in the auxiliary field subset are concatenated to obtain a representation vector of the auxiliary field subset; finally, the representation vector of the auxiliary field subset is encoded using the preset feature extractor to obtain the target description feature of the auxiliary field subset.

[0061] 1042. Perform description processing on each contract template in the preliminary template set by using the preset feature extractor to obtain a first feature group associated with the preliminary template set.

[0062] The first feature group includes descriptive features of each contract template in the preliminary template set.

[0063] Exemplarily, the following process is performed for each contract template j in the preliminary template set: first, all key fields whose field types match the field types of the auxiliary field subset are screened out from all fields of the contract template j as the clustering field set of the contract template j; then, each key field in the clustering field set of the contract template j is characterized by a feature vector to obtain a feature vector of each key field; then, the feature vectors of all key fields in the clustering field set of the contract template j are concatenated to obtain a representation vector of the contract template j; finally, the representation vector of the contract template j is encoded using a preset feature extractor to obtain the descriptive features of the contract template j. By analogy, the descriptive features of each contract template in the preliminary template set can be determined, and the descriptive features of all contract templates in the preliminary template set constitute the first feature group.

[0064] 1043. Perform clustering processing based on the second feature group to obtain a target feature group associated with the target description feature.

[0065] The second feature group includes the target description feature and each description feature of the first feature group.

[0066] Exemplarily, 1043 may specifically include the following steps a1 to a4:

[0067] a1. Obtain similarities between the description features in the second feature group to obtain a similarity set.

[0068] Specifically, feature similarities are calculated between each pair of features in the second feature group and added to the similarity set.

[0069] a2. Based on a preset similarity threshold and the similarity set, the second feature group is classified to obtain a first cluster set including a plurality of feature clusters.

[0070] Among them, the preset similarity threshold is used to limit the size of the clusters obtained by clustering in the feature vector space. The preset similarity threshold is used in the process of clustering the features of the second feature group. Specifically, each feature in the second feature group is used as the center point of a cluster, and the features of each center point within the range obtained with the similarity threshold as the radius in the feature space are determined through the similarity set. A center point and the feature set within the similarity threshold range are taken as a cluster to obtain a first cluster set.

[0071] a3. Based on a preset minimum number of single-cluster vectors, the first cluster set is divided to obtain a second cluster set.

[0072] The preset minimum number of single-cluster vectors is used to represent the number of feature vectors at least contained in each cluster.

[0073] In step a3, if the number of eigenvectors in a cluster is less than the minimum number of vectors in a single cluster, the cluster is split, and each eigenvector in the cluster is merged into other similar clusters. All clusters are checked repeatedly until the number of eigenvectors in all clusters is greater than the minimum number of vectors in a single cluster, and the second cluster set is obtained.

[0074] a4. Acquire a feature cluster associated with the target description feature from the second cluster set as the target feature group.

[0075] Therefore, through steps a1 to a4, the descriptive features of the first feature group associated with the preliminary template set and the auxiliary field subset are clustered according to similarity, the feature vector is effectively subdivided, and the target feature group associated with the descriptive features is obtained, which is conducive to the subsequent acquisition of the re-selected template set matching the auxiliary field subset based on the target feature group, improves the retrieval accuracy of the target contract template, and further improves the work efficiency of contract making.

[0076] 1044. Obtain a set of contract templates corresponding to each descriptive feature in the target feature group as a set of reselected templates matching the auxiliary field subset.

[0077] Therefore, through steps 1041 to 1044, the descriptive features of the auxiliary field subset and the descriptive features of each contract template in the preliminary template set are matched, and the re-selected template set is obtained more accurately through feature similarity, which further narrows the retrieval scope of the target contract template and improves the contract retrieval efficiency.

[0078] 105. Obtain a target contract template from the reselected template set.

[0079] There are many ways to implement step 105, which include, for example:

[0080] (1) In some embodiments, when a reselected template set is obtained in step 104, a list of contract templates corresponding to the reselected template set can be displayed on the contract management interface. When the number of contract templates contained in the reselected template set is small, the user can directly select a contract template that matches the current demand as the target contract template.

[0081] (2) In some embodiments, when a re-selected template set is obtained in step 104, a list of contract templates corresponding to the re-selected template set can be displayed on the contract management interface. When the number of contract templates contained in the re-selected template set is still large, the user can still enter further search information to match the target contract template in the re-selected template set.

[0082] With the development of the times, the scale of modern enterprises continues to expand. They involve more and more business forms in the field of e-commerce, thus generating a large number of contract templates and contracts. Contracts are the core information resources and assets of enterprises. Therefore, the management of contracts is particularly important. Timely response to electronic transaction behaviors and efficient production of contracts are conducive to the rapid advancement of electronic transaction activities and improve the business management efficiency of enterprises. Further, after searching and obtaining the target contract template in step 105, the user can modify the target contract template according to actual business needs. At this time, the user can enter a modification operation for the target contract template in the contract management interface, thereby triggering the template modification instruction of the target contract template. In response to the template modification instruction triggered by the contract management interface, the modification information of the target contract template is obtained; based on the modification information of the target contract template, the target contract template is modified and processed to obtain a new business contract.

[0083] Furthermore, in order to improve the efficiency of contract management, for example, the insurance company's contract stipulates key information such as handling fees and settlement time. In the absence of contract management, the commission settlement system needs to separately maintain key information such as handling fees for system operations, and cannot effectively perceive contract changes in a timely manner, and lacks centralized management. To this end, the modification field corresponding to the modification information of the target contract template can be used to count the contract change frequency of the target contract template in the modification field; when the contract change frequency is greater than the preset frequency threshold, the modification prompt information of the target contract template is output; wherein the modification prompt information may include suggested modification fields, suggested modification content, etc.

[0084] In order to better understand this embodiment, the use of contract template search is illustrated below with a specific example. For example, in a financial transaction scenario, the two parties to the transaction agree on cooperation and transaction forms for an insurance product. In the process of business personnel drafting an electronic contract, they need to find a matching target contract template in the predetermined contract template database. However, since this transaction is a new form of cooperation and is conducted for a new type of insurance product, there are fewer key fields that can be used for direct screening in the database, resulting in low accuracy in retrieving the target contract template using key fields, which reduces the efficiency of making contracts. In order to better make contracts in the above scenario, a more detailed analysis can be performed on the received template search instructions to narrow the search scope of the contract template to improve the retrieval efficiency and accuracy of the target contract template, thereby improving the work efficiency of making the target contract and saving manpower and material resources.

[0085] From the above content, it can be seen that the key field data set is divided by the importance indication information to obtain the primary field subset and the auxiliary field subset of the template search instruction, and the primary field subset and the auxiliary field subset are used in turn to search for the target contract template. On the one hand, since the key field matching method needs to traverse all electronic contract templates and match the key fields respectively, by using the primary field subset, the template retrieval process can pay more attention to the search template for a part of information with relatively high importance in the key field data set, reducing the problem of matching key fields with relatively low importance one by one, thereby avoiding the problem of low search efficiency caused by matching key fields; on the other hand, since some key fields of the contract template may not have associated records or the field values ​​are not completely matched, matching all key fields of the key field data set may result in some contract templates not matching. Missed search, by using the key field matching method to first search for the preliminary template set that matches the primary field subset. Since the key fields with relatively high importance will be searched using the key field matching method, it can ensure that the contract templates that match the user's needs can be accurately screened out first, thereby narrowing the retrieval scope of the contract template for the subsequent search process; then use the description feature matching method to search for the secondary template set that matches the auxiliary field subset. Since the key fields with relatively low importance will be unified into a description feature for matching, there is no need to traverse the text information of all contract templates in the database. The contract template with the highest matching degree with all fields of the auxiliary field subset can be further screened out, effectively avoiding the problem of missed search of contract templates. As a result, the search efficiency and search accuracy of contract templates can be improved, and the matching degree between the search results of contract templates and the actual demand contract templates can be improved.

[0086] In addition, in order to better implement the contract template search method in the embodiment of the present application, based on the contract template search method, a contract template search device is also provided in the embodiment of the present application, such as Figure 4FIG. 4 is a schematic diagram of a structure of a contract template search device according to an embodiment of the present application. The contract template search device 400 includes:

[0087] A response module 401 is used to respond to a template search instruction triggered by a contract management interface, and obtain a key field data set of the template search instruction and importance indication information of each field in the key field data;

[0088] A division module 402, configured to divide the key field data set based on the importance indication information of each field to obtain a primary field subset and an auxiliary field subset of the template search instruction;

[0089] Search module 403, used for matching the primary field subset with the key fields of each contract template in the preset contract template database to obtain a set of preliminary selected templates matching the primary field subset;

[0090] The search module 403 is further configured to perform matching processing based on the description features of the auxiliary field subset and the description features of each contract template in the primary selected template set, so as to obtain a secondary selected template set matching the auxiliary field subset;

[0091] The search module 403 is further configured to obtain a target contract template from the reselected template set.

[0092] In some embodiments, the search module 403 is used to:

[0093] By using a preset feature extractor, description processing is performed based on the auxiliary field subset to obtain target description features of the auxiliary field subset;

[0094] By means of the preset feature extractor, description processing is performed on each contract template in the preliminary template set to obtain a first feature group associated with the preliminary template set, wherein the first feature group includes description features of each contract template in the preliminary template set;

[0095] Performing clustering processing based on the second feature group to obtain a target feature group associated with the target description feature, wherein the second feature group includes the target description feature and each description feature of the first feature group;

[0096] A set of contract templates corresponding to each descriptive feature in the target feature group is obtained as a set of reselected templates matching the auxiliary field subset.

[0097] In some embodiments, the search module 403 is used to:

[0098] Obtaining similarities between description features in the second feature group to obtain a similarity set;

[0099] Based on a preset similarity threshold and the similarity set, the second feature group is classified to obtain a first cluster set including a plurality of feature clusters;

[0100] Based on a preset minimum number of single-cluster vectors, the first cluster set is divided to obtain a second cluster set;

[0101] A feature cluster associated with the target description feature is obtained from the second cluster set as the target feature group.

[0102] In some embodiments, the search module 403 is used to:

[0103] By using a preset feature extractor, description processing is performed based on the auxiliary field subset to obtain target description features of the auxiliary field subset;

[0104] By means of the preset feature extractor, description processing is performed on each contract template in the preliminary template set to obtain description features of each contract template in the preliminary template set;

[0105] From the preliminary template set, the top N contract templates with the highest matching degree between the description features and the target description features are obtained and added to the reselected template set.

[0106] In some embodiments, the partitioning module 402 is used to:

[0107] Determining the classification importance of each field based on the field selection order of each field and the preset field priority of each field;

[0108] Based on the classification importance of each field, each field is regarded as a primary class field or an auxiliary class field, wherein the importance of the primary class field is greater than the importance of the primary class field;

[0109] The set of the primary class fields is taken as the primary field subset, and the set of the auxiliary class fields is taken as the auxiliary field subset.

[0110] In some embodiments, the contract template search device further includes a modification module (not shown in the figure), and the modification module is used to:

[0111] In response to a template modification instruction triggered by the contract management interface, obtaining modification information of the target contract template;

[0112] Based on the modification information of the target contract template, the target contract template is modified to obtain a new business contract.

[0113] In some embodiments, the contract template search device further includes a reminder module (not shown in the figure), and the reminder module is used to:

[0114] Based on the modification field corresponding to the modification information, counting the contract change frequency of the target contract template in the modification field;

[0115] When the contract change frequency is greater than a preset frequency threshold, modification prompt information of the target contract template is output.

[0116] In specific implementation, the above-mentioned units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above-mentioned units can refer to the previous contract template search method embodiment, which will not be repeated here.

[0117] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0118] like Figure 5 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0119] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any contract template search method.

[0120] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0121] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any contract template search method.

[0122] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0123] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0124] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0125] In response to a template search instruction triggered by a contract management interface, a key field data set of the template search instruction and importance indication information of each field in the key field data are obtained; based on the importance indication information of each field, the key field data set is divided to obtain a primary field subset and an auxiliary field subset of the template search instruction; based on the primary field subset, a matching process is performed with the key fields of each contract template in a preset contract template database to obtain a preliminary template set that matches the primary field subset; based on the description features of the auxiliary field subset, a matching process is performed with the description features of each contract template in the preliminary template set to obtain a re-selected template set that matches the auxiliary field subset; and a target contract template is obtained from the re-selected template set.

[0126] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0127] Through a preset feature extractor, description processing is performed based on the auxiliary field subset to obtain a target description feature of the auxiliary field subset; through the preset feature extractor, description processing is performed on each contract template in the preliminary template set to obtain a first feature group associated with the preliminary template set, wherein the first feature group includes the description features of each contract template in the preliminary template set; clustering processing is performed based on the second feature group to obtain a target feature group associated with the target description feature, wherein the second feature group includes the target description feature and each description feature of the first feature group; a set of contract templates corresponding to each description feature in the target feature group is obtained as a re-selected template set matching the auxiliary field subset.

[0128] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0129] The similarity between the descriptive features in the second feature group is obtained to obtain a similarity set; based on a preset similarity threshold and the similarity set, the second feature group is classified to obtain a first cluster set including multiple feature clusters; based on a preset minimum number of single cluster vectors, the first cluster set is divided to obtain a second cluster set; from the second cluster set, a feature cluster associated with the target descriptive feature is obtained as the target feature group.

[0130] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0131] Through the preset feature extractor, description processing is performed based on the auxiliary field subset to obtain the target description features of the auxiliary field subset; through the preset feature extractor, description processing is performed on each contract template in the preliminary template set to obtain the description features of each contract template in the preliminary template set; from the preliminary template set, the top N contract templates with the highest matching degree between the description features and the target description features are obtained and added to the re-selected template set.

[0132] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0133] Based on the field selection order of each field and the preset field priority of each field, the classification importance of each field is determined; based on the classification importance of each field, each field is regarded as a primary class field or an auxiliary class field, wherein the importance of the primary class field is greater than the importance of the primary class field; the set of the primary class fields is regarded as the primary field subset, and the set of the auxiliary class fields is regarded as the auxiliary field subset.

[0134] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0135] In response to the template modification instruction triggered by the contract management interface, the modification information of the target contract template is obtained; based on the modification information of the target contract template, the target contract template is modified to obtain a new business contract.

[0136] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0137] Based on the modification field corresponding to the modification information, the contract change frequency of the target contract template in the modification field is counted; when the contract change frequency is greater than a preset frequency threshold, the modification prompt information of the target contract template is output.

[0138] A person of ordinary skill in the art will appreciate that all or part of the steps in the above-mentioned contract template search method may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0139] To this end, an embodiment of the present application provides a computer-readable storage medium, in which multiple computer programs are stored. The computer programs can be loaded by a processor to execute any contract template search method provided in the embodiment of the present application.

[0140] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0141] In the above-mentioned contract template search device and computer-readable storage medium embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the above-described contract template search device, computer-readable storage medium and its corresponding units can refer to the description of the contract template search method in the above embodiment, and will not be repeated here.

[0142] The above is a detailed introduction to a contract template search method, device, computer equipment and computer-readable storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and its core idea of ​​the present application; at the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application. The non-company software tools or components that appear in the embodiments of the present application are only examples and do not represent actual use.

Claims

1. A contract template search method, characterized in that: The method comprises: In response to a template search instruction triggered by a contract management interface, obtaining a key field data set of the template search instruction and importance indication information of each field in the key field data; Based on the importance indication information of each field, the key field data set is divided to obtain a primary field subset and an auxiliary field subset of the template search instruction; Based on the primary field subset, matching processing is performed with key fields of each contract template in a preset contract template database to obtain a set of preliminary selected templates matching the primary field subset; Based on the description features of the auxiliary field subset and the description features of each contract template in the primary selected template set, a matching process is performed to obtain a secondary selected template set matching the auxiliary field subset; Obtain a target contract template from the reselected template set.

2. A contract template search method according to claim 1, characterized in that: The matching process based on the description feature of the auxiliary field subset with the description feature of each contract template in the primary selected template set to obtain a secondary selected template set matching the auxiliary field subset includes: By using a preset feature extractor, description processing is performed based on the auxiliary field subset to obtain target description features of the auxiliary field subset; By means of the preset feature extractor, description processing is performed on each contract template in the preliminary template set to obtain a first feature group associated with the preliminary template set, wherein the first feature group includes description features of each contract template in the preliminary template set; Performing clustering processing based on the second feature group to obtain a target feature group associated with the target description feature, wherein the second feature group includes the target description feature and each description feature of the first feature group; A set of contract templates corresponding to each descriptive feature in the target feature group is obtained as a set of reselected templates matching the auxiliary field subset.

3. A contract template search method according to claim 2, characterized in that: The clustering process is performed based on the second feature group to obtain a target feature group associated with the target description feature, including: Obtaining similarities between description features in the second feature group to obtain a similarity set; Based on a preset similarity threshold and the similarity set, the second feature group is classified to obtain a first cluster set including a plurality of feature clusters; Based on a preset minimum number of single-cluster vectors, the first cluster set is divided to obtain a second cluster set; A feature cluster associated with the target description feature is obtained from the second cluster set as the target feature group.

4. A contract template search method according to claim 1, characterized in that: The matching process based on the description feature of the auxiliary field subset with the description feature of each contract template in the primary selected template set to obtain a secondary selected template set matching the auxiliary field subset includes: By using a preset feature extractor, description processing is performed based on the auxiliary field subset to obtain target description features of the auxiliary field subset; By means of the preset feature extractor, description processing is performed on each contract template in the preliminary template set to obtain description features of each contract template in the preliminary template set; From the preliminary template set, the top N contract templates with the highest matching degree between the description features and the target description features are obtained and added to the reselected template set.

5. A contract template search method according to claim 1, characterized in that: The importance indication information includes a field selection order and a preset field priority. The key field data set is divided based on the importance indication information of each field to obtain a primary field subset and an auxiliary field subset of the template search instruction, including: Determining the classification importance of each field based on the field selection order of each field and the preset field priority of each field; Based on the classification importance of each field, each field is regarded as a primary class field or an auxiliary class field, wherein the importance of the primary class field is greater than the importance of the primary class field; The set of the primary class fields is taken as the primary field subset, and the set of the auxiliary class fields is taken as the auxiliary field subset.

6. A contract template search method according to claim 1, characterized in that: The method further comprises: In response to a template modification instruction triggered by the contract management interface, obtaining modification information of the target contract template; Based on the modification information of the target contract template, the target contract template is modified to obtain a new business contract.

7. A contract template search method according to claim 6, characterized in that: The method further comprises: Based on the modification field corresponding to the modification information, counting the contract change frequency of the target contract template in the modification field; When the contract change frequency is greater than a preset frequency threshold, modification prompt information of the target contract template is output.

8. A contract template search device, characterized in that: The contract template searching device comprises: A response module, configured to respond to a template search instruction triggered by a contract management interface, and obtain a key field data set of the template search instruction and importance indication information of each field in the key field data; A partitioning module, configured to partition the key field data set based on the importance indication information of each field to obtain a primary field subset and an auxiliary field subset of the template search instruction; A search module, configured to perform matching processing based on the primary field subset with key fields of each contract template in a preset contract template database, and obtain a set of preliminary selected templates matching the primary field subset; The search module is further used to perform matching processing based on the description features of the auxiliary field subset and the description features of each contract template in the primary selected template set, so as to obtain a secondary selected template set matching the auxiliary field subset; The search module is also used to obtain a target contract template from the reselected template set.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is used to execute the computer program and implement the contract management method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the contract management method described in any one of claims 1 to 7.

Images