An intelligent identification system and method applied to legal documents

Abstract

The application discloses an intelligent identification system and method applied to legal documents, relates to the technical field of document intelligent identification, acquires fill-in data of a customer filling in a two-form element type, carries out pretreatment and normalization on the fill-in data, obtains fill-in characteristics of the two-form element type task, successfully processes the two-form element type task, establishes a service personnel database according to the characteristics of the successfully processed two-form element type task, selects adaptive service personnel, selects selected service personnel of a new two-form element type task according to the busy case number of the service personnel, comprehensively considers the adaptive degree of the fill-in characteristics, selects service personnel with the highest adaptive degree as the selected service personnel of the new two-form element type task, and if the customer is not satisfied with the new two-form element type task, the selected service personnel serves the customer again. The application has the capability of continuously optimizing the service system by means of a continuous change model, so that subsequent matching is more in line with the core needs of the customer.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of intelligent identification of documents, in particular to an intelligent identification system and method applied to legal documents. BACKGROUND

[0002] In the field of legal document processing, the filling of element type complaints and answers and the subsequent service docking lack unified standards. In the traditional mode, the document format has high flexibility but different standards, and customers are prone to omit content, have ambiguous expressions or format confusion when filling in, which leads to great difficulty in subsequent information sorting. At the same time, the original data filled in by customers lack systematic preprocessing procedures, and the information is scattered and has different formats, which requires a lot of manpower for screening, proofreading and integration, not only prolonging the task starting period, but also being prone to errors due to manual operation, affecting the overall service efficiency. In addition, the filling habits of different customers differ greatly, further increasing the difficulty of data standardization processing and restricting the efficient promotion of legal document services. The allocation of service personnel for current element type legal document tasks mainly depends on manual judgment or simple experience matching, and lacks a scientific and perfect personnel capability evaluation system. The existing mode does not fully integrate the historical successful case characteristics of service personnel, and cannot accurately identify the task types and service fields they are good at, resulting in low matching degree of personnel allocation and task demand. In some cases, service personnel with corresponding experience are not preferentially recommended, and personnel with inconsistent experience are prone to service deviation after taking up the task, affecting the professionalism and accuracy of document processing. At the same time, the workload difference is not fully considered in the personnel allocation process, which may lead to task accumulation of some personnel and resource idling of some personnel, causing waste of human resources and difficulty in guaranteeing the stability of service quality. The existing service system lacks dynamic optimization mechanism and effective customer feedback loop. In the face of new element type legal document tasks, the traditional matching mode is difficult to quickly adapt to new task characteristics, and still uses fixed allocation logic, resulting in lag in service response. In addition, the feedback of customers on service results cannot be effectively converted into optimization basis, and problems in the service process cannot be fed back to the personnel matching link in time, so that similar problems recur. At the same time, the weight division and dynamic adjustment of different task characteristics cannot be accurately focused on the core needs of customers, and in the long term, the service mode is prone to solidification and difficult to adapt to diversified and complex legal document processing needs, and customer satisfaction is difficult to continuously improve. SUMMARY

[0003] The purpose of the present application is to provide an intelligent identification system and method applied to legal documents to solve the problems raised in the background art.

[0004] In order to solve the above technical problems, the present application provides the following technical scheme: an intelligent identification method applied to legal documents, comprising the following steps:

[0005] S1, a format is specified for the element type two form, blank data filled in by the customer is obtained, the blank data is preprocessed and normalized, and blank features of the element type two form task are obtained;

[0006] S2, the service personnel are analyzed, the element type two form task is successfully processed, and a service personnel database is established according to the features of the successfully processed element type two form task;

[0007] S3, when a new element type two form appears, a new element type two form preset task is established, the adaptation degree of the service personnel to the new element type two form preset task is analyzed, and the adaptive service personnel is selected;

[0008] S4, when there is adaptive service personnel for the new element type two form task, the selected service personnel for the new element type two form task is selected according to the number of busy cases of the service personnel;

[0009] S5, when there is no adaptive service personnel for the new element type two form task, the adaptive degree of the blank feature is comprehensively considered, and the service personnel with the highest adaptive degree is selected as the selected service personnel for the new element type two form task;

[0010] S6, after the service is completed, if the customer is not satisfied with the new element type two form task, the selected service personnel is analyzed again to serve the customer.

[0011] Further, in step S1, the element type two form includes the element type complaint and the element type answer, the element type two form is specified as a fixed table format, the table format is a fixed blank item, the blank item option is provided for the customer to select and fill in the blank item, and then the blank data in the element type two form item option is obtained. The blank data is preprocessed and normalized, and N blank features of the element type two form task are obtained after preprocessing and normalization. By unifying the fixed table format of the element type two form, the blank item is specified and the corresponding optional content is provided, the difficulty of filling in by the customer is greatly reduced, the rework problem caused by non-uniform format, ambiguous expression or content omission is avoided, and the filling process is more smooth and efficient. At the same time, the collected blank data is preprocessed and normalized, invalid information is effectively eliminated, data format is regularized, data standardization is realized, human labor investment and error risk of subsequent information arrangement are reduced, accurate blank features are extracted, reliable and unified data support is provided for the subsequent service personnel matching link, and the efficient promotion of the overall service process is facilitated.

[0012] Further, in step S2, the service personnel for the xth element two-state task is analyzed, and for the xth service personnel, x = 1, 2, …, X, the number of successful processing element two-state tasks of the xth service personnel in the historical data is Y, and the xth successful processing element two-state task means that after the xth service personnel serves the element two-state task, the customer feedback is satisfied with the element two-state task, and then the characteristics of the yth successful processing element two-state task are obtained {A y_1 , y_2 , …, y_n , …, y_N} where A y_n represents the nth fill-in characteristic of the yth successful processing element two-state task, and y = 1, 2, …, Y is substituted to obtain the characteristics of Y successful processing element two-state tasks, and a service personnel database is established according to the characteristics of the successful processing element two-state task; by focusing on the customer satisfaction cases of the service personnel, the task characteristics are extracted and the service personnel database is constructed, which effectively integrates the historical successful experience of the service personnel. The database clearly presents the task types and core capabilities that each service personnel is good at, avoiding the disadvantages of relying on subjective judgment or scattered experience in traditional personnel capability assessment. The successful cases on which the database relies are based on customer feedback, ensuring the authenticity and effectiveness of the information, providing solid data support for subsequent task and personnel matching, making personnel capability assessment more objective and targeted, and helping to improve the scientificity and reliability of overall service matching.

[0013] Further, in step S3, when a new element two-state task occurs, a new element two-state preset task is established, and the adaptation degree of the service personnel to the new element two-state preset task is analyzed, and the fill-in characteristics of the new element two-state preset task are {A1, A2, …, A n , …, N} where A n represents the nth fill-in characteristic of the new element two-state preset task, and for the xth service personnel, the service personnel database is called, and the matching degree B y of the yth successful processing element two-state task and the new element two-state preset task is analyzed:

[0014] ;

[0015] where k n represents the nth fill-in characteristic weight, and then the matching relationship between the yth successful processing element two-state task and the new element two-state preset task is judged, and when B yWhen >C, it is determined that the y-th successfully processed element-type two-state task matches the new element-type two-state preset task, and the y-th successfully processed element-type two-state task is a matching element-type two-state task of the new element-type two-state preset task; otherwise, it is determined that the y-th successfully processed element-type two-state task does not match the new element-type two-state preset task, and the y-th successfully processed element-type two-state task is not a matching element-type two-state task of the new element-type two-state preset task.

[0016] Substituting y = 1, 2, ..., Y into each element, the matching relationship between Y successfully processed element-based two-state tasks and the new element-based two-state preset task is determined. This yields the Y0 matching element-based two-state task for the x-th service personnel. If Y0 is not 0, the x-th service personnel is listed as a suitable service personnel; otherwise, the x-th service personnel is listed as a candidate service personnel. Substituting x = 1, 2, ..., X into each element, Q suitable service personnel for the new element-based two-state preset task are obtained, and these suitable service personnel are added to the suitable service personnel directory for the new element-based two-state preset task. By analyzing the matching relationship between the new element-based two-state preset task and the service personnel's historical successful cases, suitable service personnel with corresponding service experience are accurately selected. This process relies on the characteristics of real successful cases for matching, eliminating the drawbacks of subjective experience judgment and ensuring that the selected suitable personnel can meet the fill-in-the-blank characteristics requirements of the new task. Clearly identifying highly suitable personnel as suitable candidates not only provides a precise personnel reserve for new task allocation but also maximizes the professional advantages of service personnel, effectively reducing service deviations caused by mismatched capabilities. This improves the accuracy of task-person matching from the source and lays a solid foundation for the stable guarantee of subsequent service quality.

[0017] Furthermore, in step S4, when a user issues a service request, the preset task for the new element-based two-state task is transformed into a new element-based two-state task. The number of suitable service personnel is analyzed. When Q is not 0, it is determined that there are suitable service personnel for the new element-based two-state task. The Q-th suitable service personnel are analyzed, and the creation time of the new element-based two-state task is retrieved. The number of busy cases for the q-th suitable service personnel is E. q The number of busy cases refers to the number of element-based two-state tasks that the assigned service personnel have not completed within a preset period starting from the establishment time. Uncompleted element-based two-state tasks represent the element-based two-state tasks within a preset period starting from the establishment time. Substituting each into q=1,2,…,Q, we obtain the number of busy cases {E1,E2,…,E...} for Q assigned service personnel. q ,…,E Q}, where E qThe busy case number of the qth adaptive service personnel is represented, and then the adaptive service personnel with the least busy case number is selected as the selected service personnel of the new element type two-status task; task allocation is performed by combining the busy case situation of the adaptive service personnel, thereby effectively realizing dynamic balance of human resources. This mechanism avoids the decline in service quality caused by task accumulation of adaptive personnel, ensures that each personnel undertaking a task can carry out service under reasonable work load, guarantees service efficiency, and maintains the stability of service quality. At the same time, the personnel with the least busy case is preferentially selected, so that the new task can be responded and processed in time, the customer waiting time is reduced, and the timeliness and customer satisfaction of service are improved. This allocation mode can also fully play the professional value of adaptive personnel, avoid resource idling or excessive saturation, and optimize the operation efficiency of the service system as a whole, thereby realizing efficient adaptation of tasks and personnel.

[0018] Further, in step S5, when Q is 0, it is judged that there is no adaptive service personnel for the new element type two-status task, the xth service personnel is analyzed, for the nth blank feature of the xth service personnel, the nth blank feature of the yth successfully processed element type two-status task is {A 1_n ,A 2_n ,…,A y_n ,…,A Y_n}, for the nth blank feature of the yth successfully processed element type two-status task, the difference degree between the nth blank feature of the yth successfully processed element type two-status task and the nth blank feature of the new element type two-status task is F n_y , F n_y =|(A y_n -A n ) / A y_n |, when F n_y <F y , it is judged that the nth blank feature of the yth successfully processed element type two-status task is similar to the nth blank feature of the new element type two-status task; otherwise, it is judged that the nth blank feature of the yth successfully processed element type two-status task is not similar to the nth blank feature of the new element type two-status task, and then the adaptive feature number G n_x of the nth blank feature of the xth service personnel is obtained, which represents the number of blank features that meet the similarity with the nth blank feature of the new element type two-status task in the nth blank feature of the yth successfully processed element type two-status task. x=1, 2, …, X is substituted one by one to obtain the adaptive feature number {G n_1 ,G n_2 ,…,G n_x ,…,G n_X} of the nth blank feature of the Xth service personnel, and then the adaptive score H n_x of the nth blank feature of the xth service personnel is obtained.

[0019] ;

[0020] Substitute n = 1, 2, …, N, to obtain the N fill-in feature adaptation scores of the xth service personnel, and then obtain the comprehensive score J of the xth service personnel x , J x is the sum of the N fill-in feature adaptation scores of the xth service personnel, substitute x = 1, 2, …, X, to obtain the comprehensive score of the X service personnel, and select the service personnel with the highest comprehensive score as the selected service personnel of the new element type task; when there is no adaptive service personnel, this mechanism quantitatively evaluates the degree of personnel adaptation by analyzing the similarity between the historical successful cases of the service personnel and the fill-in features of the new task, avoiding the deviation of subjective judgment. It compares one by one from the fill-in feature dimension, calculates the adaptation score and the comprehensive score, so that the personnel selection has an objective and detailed basis, ensuring that even in the absence of direct experience matching, the service personnel most suitable for the new task can be selected. This way effectively fills the matching gap when there is no adaptive personnel, ensures the scientificity of task allocation and the stability of service quality, maximizes customer demand, and improves the overall adaptability of service and customer satisfaction.

[0021] Further, in step S6, after the service of the new element type task is completed, if the customer feedback on the new element type task is not satisfied, the fill-in feature that the customer is not satisfied with is called, and if the nth fill-in feature is the fill-in feature that the customer is not satisfied with, the weight of the nth fill-in feature is replaced by α*k n , α is a preset weight amplification coefficient, α > 1, and the selected service personnel is again analyzed to serve the customer; a dynamic optimization closed loop of service feedback is constructed, and the feedback of the customer who is not satisfied is accurately converted into the basis for adjusting the weight of the fill-in feature. By amplifying the weight of the corresponding feature, the subsequent service personnel analysis focuses more on the customer's core concerns, effectively avoiding the repeated occurrence of similar service deviations, and improving the pertinence and repair efficiency of the service. At the same time, this iterative mechanism based on real feedback enables the service system to continuously adapt to changes in customer demand, constantly improve the matching logic, and ensure the stability of service quality and the improvement of customer satisfaction from a long-term perspective, forming a virtuous cycle of "service-feedback-optimization-re-service".

[0022] An intelligent recognition system applied to legal documents, the system comprising: a fill-in data feature extraction module, a service personnel library construction module, a new task adaptation module, a busy degree screening and selection module, a feature adaptation highest selection module, and a feedback secondary analysis module;

[0023] The fill-in data feature extraction module is used for obtaining fill-in data of the customer filling in the element type legal document, pre-processing and normalizing the fill-in data, and obtaining N fill-in features of the element type legal document task according to the element type legal document format;

[0024] The service personnel database construction module is used for analyzing the service personnel, calling the successfully processed element type legal document task, and establishing a service personnel database according to the features of the successfully processed element type legal document task.

[0025] The new task adaptation module is used for establishing a new element type legal document preset task when a new element type legal document appears, analyzing the adaptation degree of the service personnel to the new element type legal document preset task, and selecting the adaptive service personnel.

[0026] The busy degree screening and selection module is used for selecting the selected service personnel of the new element type legal document task according to the number of busy cases of the service personnel when the adaptive service personnel of the new element type legal document task exists.

[0027] The feature adaptation highest selection module is used for selecting the service personnel with the highest adaptation degree as the selected service personnel of the new element type legal document task when the adaptive service personnel of the new element type legal document task does not exist, and comprehensively considering the adaptation degree of the fill-in feature.

[0028] The feedback secondary analysis module is used for reanalyzing the selected service personnel to serve the customer again after the service is completed if the customer is not satisfied with the new element type legal document task.

[0029] Compared with the prior art, the beneficial effects achieved by the present application are: on the one hand, by standardizing the fixed format of the element type legal document, the fill-in items and the optional range are clearly defined, the customer filling process is more clear and smooth, and the rework caused by inconsistent format or ambiguous filling is reduced. The data preprocessing and normalization steps simplify the information sorting steps, avoid the tedious operation of manual screening and correction, and greatly shorten the preparation time of the task. At the same time, the construction of the service personnel database integrates the historical service experience, and there is no need to reevaluate the personnel ability every time, so that the task docking process is more efficient, the time and labor cost is effectively reduced, and the overall service operation rate is improved.

[0030] On the one hand, the service personnel database established by the successful case features provides a reliable basis for task matching. By analyzing the adaptation degree of the task fill-in feature and the historical successful case of the service personnel, the personnel with corresponding service ability are accurately selected, and it is ensured that the service personnel who undertake the task can meet the customer's demand. Whether the adaptive personnel with relevant experience is selected first or the personnel with the highest adaptation degree is selected through comprehensive scoring, the professional advantages of the service personnel can be maximized, the service deviation caused by the mismatch of ability can be reduced, the professionalism and accuracy of the legal document processing can be effectively guaranteed, and the customer trust can be enhanced.

[0031] On the other hand, the service system is integrated with the ability of continuous optimization, and the weight of the corresponding blank feature is adjusted for the unsatisfied service scene, so that the subsequent matching is more in line with the core needs of customers. This dynamic adjustment mode can continuously adapt to various new element type legal document tasks, avoiding the limitations brought by the solidification of service mode. At the same time, the personnel screening standard takes into account the experience adaptation and the work load, which not only ensures the service quality, but also realizes the reasonable allocation of human resources, forms a virtuous cycle of "matching-service-feedback-optimization", and continuously improves the stability and adaptability of the service system in the long run, better meeting the diversified legal document processing needs. BRIEF DESCRIPTION OF DRAWINGS

[0032] The accompanying drawings are included to provide a further understanding of the application, and constitute a part of the specification, which together with the embodiments of the application are used to explain the application, and do not constitute a limitation on the application. In the drawings:

[0033] Figure 1 is a structural diagram of an intelligent recognition system applied to legal documents according to the application;

[0034] Figure 2 is a flowchart of an intelligent recognition method applied to legal documents according to the application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the application will be described in detail below with reference to the drawings of the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0036] Please refer to Figure 1 and Figure 2 The application provides a technical solution: an intelligent recognition method applied to legal documents, comprising the following steps:

[0037] S1, the format of the element type legal document is specified, the blank data filled in the element type legal document by the customer is obtained, the blank data is preprocessed and normalized, and the blank features of the element type legal document task are obtained;

[0038] S2, the service personnel are analyzed, the successfully processed element type legal document tasks are called, and a service personnel database is established according to the characteristics of the successfully processed element type legal document tasks;

[0039] S3, when a new element type legal document appears, a new element type legal document preset task is established, the adaptation degree of the service personnel to the new element type legal document preset task is analyzed, and the adaptive service personnel are selected;

[0040] S4, when an adaptive service personnel for the new element type two-form task exists, a selected service personnel of the new element type two-form task is selected according to the busy case quantity of the service personnel;

[0041] S5, when an adaptive service personnel for the new element type two-form task does not exist, a selected service personnel of the new element type two-form task is selected by comprehensively considering the adaptive degree of the fill-in feature;

[0042] S6, after the service is completed, if the customer feedbacks dissatisfaction with the new element type two-form task, the selected service personnel serves the customer again.

[0043] In step S1, the element type two-form is specified as a fixed table format, the element type two-form includes an element type complaint and an element type answer, the element type two-form is specified as a fixed table format, the table format is a fixed fill-in item, the fill-in item option is used for being selected by the customer to fill in the fill-in item, and then the fill-in data in the element type two-form item option is obtained, the fill-in data is preprocessed and normalized, the N fill-in features of the element type two-form task are obtained after preprocessing and normalization, the fixed table format of the element type two-form is unified, the fill-in item is clear and the corresponding optional content is provided, the difficulty of filling is greatly reduced, the rework problem caused by non-uniform format, ambiguous expression or content omission is avoided, and the filling process is more smooth and efficient. At the same time, the collected fill-in data is preprocessed and normalized, invalid information is effectively eliminated, the data format is regularized, data standardization is realized, the human input and error risk of subsequent information sorting are reduced, accurate fill-in features are extracted, reliable and unified data support is provided for the subsequent service personnel matching link, and the efficient promotion of the overall service process is facilitated.

[0044] In step S2, the service personnel for the X-position interfacing element type two-form task is analyzed, for the xth service personnel, x=1, 2, …, X, the number of successfully handled element type two-form tasks of the xth service personnel in the historical data is Y, the successfully handled element type two-form task of the xth position indicates that the customer feedback is satisfied with the element type two-form task after the xth service personnel serves the element type two-form task, and then the features of the yth successfully handled element type two-form task are obtained. y_1 ,A y_2 ,…,A y_n ,…,A y_N} are obtained, wherein A y_nLet y represent the nth fill-in-the-blank feature of the y-th successfully processed element-based two-state task. Substituting each of these features into y=1,2,…,Y yields the features of Y successfully processed element-based two-state tasks. A service personnel database is then established based on these features. By focusing on customer satisfaction cases of service personnel, task features are extracted and used to construct the database, effectively integrating the historical success experiences of service personnel. This database clearly presents the task types and core competencies that each service personnel excels in, avoiding the drawbacks of traditional personnel competency assessments that rely on subjective judgment or fragmented experience. The success cases upon which the database is based are centered on customer feedback, ensuring the authenticity and effectiveness of the information. This provides solid data support for the accurate matching of subsequent tasks and personnel, making personnel competency assessments more objective and targeted, and contributing to improving the scientific rigor and reliability of overall service matching.

[0045] In step S3, when a new element-type two-state condition appears, a preset task for the new element-type two-state condition is established. The adaptability of service personnel to the preset task for the new element-type two-state condition is analyzed. The fill-in-the-blank characteristics of the preset task for the new element-type two-state condition are {A1, A2, ..., A...}. n ,…,A N}, where A n Let n be the fill-in-the-blank feature of the new element-based two-state preset task. For the x-th service personnel, call the service personnel database and analyze the matching degree B between the y-th successfully processed element-based two-state task and the new element-based two-state preset task. y :

[0046] ;

[0047] Where k n This represents the preset weight of the nth fill-in-the-blank feature, which is then used to determine the matching relationship between the yth successfully processed element-based two-state task and the new element-based two-state preset task. When B y When >C, it is determined that the y-th successfully processed element-type two-state task matches the new element-type two-state preset task, and the y-th successfully processed element-type two-state task is a matching element-type two-state task of the new element-type two-state preset task; otherwise, it is determined that the y-th successfully processed element-type two-state task does not match the new element-type two-state preset task, and the y-th successfully processed element-type two-state task is not a matching element-type two-state task of the new element-type two-state preset task.

[0048] Substitute y = 1, 2, …, Y, judge the matching relationship between Y pieces of successfully processed element type two-state tasks and new element type two-state preset tasks, obtain Y0 pieces of matching element type two-state tasks of the xth service personnel for the new element type two-state preset task, if Y0 is not 0, list the xth service personnel as an adaptive service personnel; otherwise, list the xth service personnel as an alternative service personnel, substitute x = 1, 2, …, X, obtain Q adaptive service personnel for the new element type two-state preset task, put the adaptive service personnel into the adaptive service personnel directory for the new element type two-state preset task; through analyzing the adaptive relationship between the new element type two-state preset task and the service personnel historical successful cases, accurately select the adaptive service personnel with corresponding service experience. This process relies on the characteristics of real successful cases for matching, discards the disadvantages of subjective experience judgment, and ensures that the selected adaptive personnel can meet the needs of the new task. The personnel with high adaptability are explicitly listed as adaptive team, which not only provides accurate personnel reserve for new task allocation, but also maximizes the professional advantages of service personnel, effectively reduces the service deviation caused by mismatch of ability, improves the matching accuracy of task and personnel from the source, and lays a solid foundation for stable service quality.

[0049] In step S4, when the user issues a service demand, the new element type two-state preset task is converted into a new element type two-state task, the number of adaptive service personnel is analyzed, when Q is not 0, it is judged that there is an adaptive service personnel for the new element type two-state task, the Q adaptive service personnel are analyzed, the establishment time of the new element type two-state task is called, and the busy case number of the qth adaptive service personnel is E q , the busy case number is the number of element type two-state tasks that the adaptive service personnel has not completed within a preset period starting from the establishment time, the element type two-state task that has not been completed represents an element type two-state task within a preset period starting from the establishment time, substitute q = 1, 2, …, Q, obtain the busy case number {E1, E2, …, E q , …, E Q} of the Q adaptive service personnel, wherein E qThe busy case number of the qth adaptive service personnel is represented, and then the adaptive service personnel with the least busy case number is selected as the selected service personnel of the new element type two-status task; through task allocation combined with the busy case situation of the adaptive service personnel, the dynamic balance of human resources is effectively realized. This mechanism avoids the decline of service quality caused by task accumulation of adaptive personnel, ensures that each personnel who undertakes the task can carry out service under reasonable work load, guarantees service efficiency, and maintains the stability of service quality. At the same time, the personnel with the least busy case is preferentially selected, so that the new task can be responded and processed in time, the customer waiting time is reduced, and the timeliness and customer satisfaction of service are improved. This allocation mode can also fully play the professional value of adaptive personnel, avoid resource idling or excessive saturation, and optimize the operation efficiency of the service system as a whole, realizing efficient adaptation of tasks and personnel.

[0050] In step S5, when Q is 0, it is judged that there is no adaptive service personnel for the new element type two-status task, the Xth service personnel is analyzed, and for the nth blank feature of the xth service personnel, the nth blank feature of the Yth successfully processed element type two-status task is {A 1_n ,A 2_n ,…,A y_n ,…,A Y_n}, for the nth blank feature of the yth successfully processed element type two-status task, the difference degree between the nth blank feature of the yth successfully processed element type two-status task and the nth blank feature of the new element type two-status task is F n_y , F n_y =|(A y_n -A n ) / A y_n |, when F n_y <F y , it is judged that the nth blank feature of the yth successfully processed element type two-status task is similar to the nth blank feature of the new element type two-status task; otherwise, it is judged that the nth blank feature of the yth successfully processed element type two-status task is not similar to the nth blank feature of the new element type two-status task, and then the adaptive feature number G n_x of the nth blank feature of the xth service personnel is obtained, which represents the number of blank features that meet the similarity with the nth blank feature of the new element type two-status task in the nth blank feature of the Yth successfully processed element type two-status task. x=1,2,…,X is substituted one by one to obtain the adaptive feature number {G n_1 ,G n_2 ,…,G n_x ,…,G n_X} of the nth blank feature of the Xth service personnel, and then the adaptive score H n_x of the nth blank feature of the xth service personnel is obtained.

[0051] ;

[0052] Substitute n = 1, 2, …, N to obtain N fill-in feature adaptation scores of the xth service personnel, and then obtain the comprehensive score J of the xth service personnel x , J x is the sum of the N fill-in feature adaptation scores of the xth service personnel, substitute x = 1, 2, …, X to obtain the comprehensive score of the X service personnel, and select the service personnel with the highest comprehensive score as the selected service personnel of the new element type two-state task; when there is no adaptive service personnel, the mechanism quantitatively evaluates the degree of personnel adaptation by analyzing the similarity between the historical successful cases of the service personnel and the fill-in features of the new task, avoiding the deviation of subjective judgment. It compares and calculates the adaptation score and the comprehensive score from the fill-in feature dimension one by one, so that the personnel selection has an objective and detailed basis, ensuring that even in the absence of direct experience matching, the service personnel most suitable for the new task can be selected. This way effectively fills the matching gap when there is no adaptive personnel, ensures the scientificity of task allocation and the stability of service quality, maximizes customer demand, and improves the overall adaptability of service and customer satisfaction.

[0053] In step S6, after the service of the new element type two-state task is completed, if the customer feedback on the new element type two-state task is not satisfied, the fill-in feature that the customer is not satisfied with is called, and if the nth fill-in feature is the fill-in feature that the customer is not satisfied with, the weight of the nth fill-in feature is replaced by α*k n , α is a preset weight amplification coefficient, α > 1, and the selected service personnel serves the customer again; a dynamic optimization closed loop of service feedback is constructed, and the feedback of the customer who is not satisfied is accurately converted into the basis for adjusting the weight of the fill-in feature. By amplifying the weight of the corresponding feature, the subsequent service personnel analysis focuses more on the customer's core concerns, effectively avoiding the repeated occurrence of similar service deviations, and improving the pertinence and repair efficiency of the service. At the same time, this iterative mechanism based on real feedback enables the service system to continuously adapt to changes in customer demand, continuously improve the matching logic, and ensure the stability of service quality and the improvement of customer satisfaction from a long-term perspective, forming a virtuous cycle of “service-feedback-optimization-re-service”.

[0054] An intelligent recognition system applied to legal documents, the system comprises: a fill-in data feature extraction module, a service personnel library construction module, a new task adaptation module, a busy degree screening and selection module, a feature adaptation highest selection module, and a feedback secondary analysis module;

[0055] The fill-in data feature extraction module is used to obtain the fill-in data of the customer for the element type two-state by extracting the fill-in data feature of the element type two-state from the element type two-state regulation format, pre-process and normalize the fill-in data, and obtain N fill-in features of the element type two-state task;

[0056] The service personnel library construction module is used for analyzing service personnel, calling successful processing element type two status tasks, and establishing a service personnel database according to characteristics of the successful processing element type two status tasks;

[0057] The new task adaptation module is used for establishing a new element type two status preset task when a new element type two status appears, analyzing the adaptation degree of the service personnel to the new element type two status preset task, and selecting an adapted service personnel;

[0058] The busy degree screening selection module is used for selecting a selected service personnel for the new element type two status task according to the number of busy cases of the service personnel when there is an adapted service personnel for the new element type two status task;

[0059] The characteristic adaptation highest selection module is used for comprehensively considering the adaptation degrees of the blank characteristics and selecting a service personnel with the highest adaptation degree as the selected service personnel for the new element type two status task when there is no adapted service personnel for the new element type two status task;

[0060] The feedback secondary analysis module is used for reanalyzing the selected service personnel for the customer service if the customer feedback is not satisfied with the new element type two status task after the service is completed.

[0061] Embodiment 1: A customer needs to submit an element type complaint due to a contract dispute, and the implementation process of the method is started.

[0062] Enter step S1, the system standardizes the element type complaint into a fixed table format, and sets fixed blank items such as “dispute type”, “contract subject”, “breach of contract situation” and the like in the table, and provides clear options for each item for the customer to select. After the customer completes the option filling according to the own situation, the system pre-processes the collected blank data, cleans up invalid information, and normalizes the format, and then extracts a plurality of blank characteristics of the complaint task through normalization processing, thereby laying a data foundation for subsequent operations.

[0063] Enter step S2, the system analyzes a plurality of service personnel who interface with the element type two status tasks. Taking service personnel Zhang San and Li Si as examples, the system calls historical cases of element type two status tasks successfully processed and with satisfied customer feedback, extracts the blank characteristics in the cases, and establishes a service personnel database, wherein the successful cases of Zhang San are mostly concentrated in the contract dispute field, and Li Si is outstanding in the infringement case.

[0064] When the contract dispute complaint appears as a new-element two-form preset task, step S3 is entered. The system calls the service personnel database to analyze the matching degree of the successful cases of service personnel such as Zhang San, Li Si, and the new task. Through one-by-one comparison of the case characteristics and the new task fill-in characteristics, it is determined that the successful cases of Zhang San have a higher matching degree with the new task, and therefore Zhang San is listed as an adaptive service personnel, while Li Si is listed as an alternative because the field he is good at does not match.

[0065] After the user issues a service demand, the new-element two-form preset task is converted into a new task, and step S4 is entered. The system analyzes the number of adaptive service personnel and finds that there is only Zhang San. Further analysis of the number of busy cases of Zhang San, i.e., the number of two-form preset tasks that have not been completed by Zhang San within a preset period, finds that the current task load of Zhang San is moderate, and therefore Zhang San is selected as the service personnel of the new task.

[0066] Suppose that there is no adaptive service personnel at this time, step S5 is entered. The system analyzes all service personnel. Taking service personnel Wang Wu as an example, although he has no direct contract dispute successful case, the system compares the similarity of the fill-in characteristics of his historical successful cases and the fill-in characteristics of the new task, calculates the adaptive score of each characteristic, and finally the comprehensive score of Wang Wu is the highest, and therefore Wang Wu is selected to undertake the task.

[0067] After Zhang San completes the service, if the customer is not satisfied with the service of the contract dispute complaint, and the dissatisfaction points are concentrated on the "contract clause interpretation" related fill-in characteristics, step S6 is entered. The system calls the dissatisfied fill-in characteristics, amplifies the weight thereof, analyzes the service capability of Zhang San again, and adjusts the subsequent task allocation logic of Zhang San to avoid similar dissatisfaction from occurring again, so as to realize dynamic optimization of the service system.

[0068] It will be obvious to a person skilled in the art that the application is not limited to the details of the exemplary sensor device embodiments described above, but that the application can be implemented in other embodiments without departing from the spirit or essential characteristics of the application. The embodiments should, therefore, be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the description above, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference signs in the claims should be considered as limiting the scope of the claims.

Claims

1. An intelligent identification method applied to legal documents, characterized in that: The method comprises the following steps: S1, a format of an element type two form is specified, blank data filled in the element type two form by a client is obtained, the blank data is preprocessed and normalized, and blank characteristics of the element type two form task are obtained; S2, service personnel are analyzed, successfully processed element type two form tasks are called, and a service personnel database is established according to characteristics of the successfully processed element type two form tasks; S3, when a new element type two form appears, a new element type two form preset task is established, an adaptation degree of the service personnel to the new element type two form preset task is analyzed, and adaptive service personnel are selected; S4, when adaptive service personnel exist for the new element type two form task, selected service personnel for the new element type two form task are selected according to a busy case number of the service personnel; S5, when adaptive service personnel do not exist for the new element type two form task, the selected service personnel are selected as selected service personnel for the new element type two form task by comprehensively considering an adaptation degree of the blank characteristics; S6, after service is completed, if the client is not satisfied with the new element type two form task, the selected service personnel serve the client again; In step S1, the element type two form is specified, the element type two form includes an element type complaint and an element type answer, the element type two form is specified as a fixed table format, the table format is a fixed blank item, blank item options are provided for the client, the blank item options are used to be selected and filled in by the client, and then blank data in the element type two form item options is obtained, the blank data is preprocessed and normalized, and N blank characteristics of the element type two form task are obtained after preprocessing and normalization; In step S2, the service personnel of the xth position for the element two-state task is analyzed, and for the xth service personnel, x = 1, 2, …, X, the number of successful processing element two-state tasks of the xth service personnel in the historical data is Y, the xth successful processing element two-state task means that the customer feedback is satisfied after the xth service personnel serves the element two-state task, and then the characteristics of the yth successful processing element two-state task are obtained {A y_1 ,A y_2 ,…,A y_n ,…,A y_N} wherein A y_n represents the nth fill-in characteristic of the yth successful processing element two-state task, y = 1, 2, …, Y is substituted to obtain the characteristics of Y successful processing element two-state tasks, and a service personnel database is established according to the characteristics of the successful processing element two-state tasks; In step S3, when a new element formula two-state appears, a new element formula two-state preset task is established, and the degree of adaptation of the service personnel to the new element formula two-state preset task is analyzed. The fill-in characteristics of the new element formula two-state preset task are {A1, A2, …, A n ,…,A N}, wherein A n represents the nth fill-in characteristic of the new element formula two-state preset task. For the xth service personnel, the service personnel database is called, and the matching degree B y of the yth successfully processed element formula two-state task and the new element formula two-state preset task is analyzed. ； wherein k n represents a preset nth blank feature weight, and then a matching relationship between the yth successfully processed element type two-state task and the new element type two-state preset task is judged. When B y >C, it is judged that the yth successfully processed element type two-state task matches the new element type two-state preset task, and the yth successfully processed element type two-state task is a matching element type two-state task of the new element type two-state preset task; otherwise, it is judged that the yth successfully processed element type two-state task does not match the new element type two-state preset task, and the yth successfully processed element type two-state task is not a matching element type two-state task of the new element type two-state preset task. 2.The intelligent identification method applied to legal documents according to claim 1, characterized in that: Y is substituted into y=1, 2, …, Y, a matching relationship of Y pieces of successfully processed element type two form tasks and the new element type two form preset task is judged, Y0 pieces of matching element type two form tasks of the new element type two form preset task for the xth service personnel are obtained, if Y0 is not 0, the xth service personnel are listed as adaptive service personnel, otherwise, the xth service personnel are listed as alternative service personnel, x is substituted into x=1, 2, …, X, Q adaptive service personnel for the new element type two form preset task are obtained, and the adaptive service personnel are put into an adaptive service personnel directory for the new element type two form preset task. 3.The intelligent identification method for legal documents of claim 2, characterized in that: In step S4, when the user issues a service demand, the new-element two-status preset task is converted into a new-element two-status task, the number of adaptive service personnel is analyzed, when Q is not 0, it is judged that there is adaptive service personnel for the new-element two-status task, the Qth adaptive service personnel is analyzed, the establishment time of the new-element two-status task is called, and the busy case number of the qth adaptive service personnel is E q , the busy case number is the number of adaptive service personnel unfinished element two-status tasks within a preset period with the establishment time as the starting point, the unfinished element two-status task indicates an element two-status task within a preset period with the establishment time as the starting point, q=1, 2, …, Q are substituted, and the busy case numbers of Q adaptive service personnel {E1, E2, …, EQ} are obtained. q … Q}, wherein E q represents the busy case number of the qth adaptive service personnel, and then the adaptive service personnel with the least busy case number is selected as the selected service personnel of the new-element two-status task.

4. The intelligent identification method for legal documents according to claim 3, characterized in that: In step S5, when Q is 0, it is judged that there is no adaptive service personnel for the new element type two-state task, the xth service personnel is analyzed, for the xth service personnel, the nth blank characteristic of the nth successful element type two-state task is {A 1_n ,A 2_n ,…,A y_n ,…,A Y_n}, for the yth successful element type two-state task, the difference degree between the nth blank characteristic of the yth successful element type two-state task and the nth blank characteristic of the new element type two-state task is F n_y , F n_y =|(A y_n -A n ) / A y_n |, when F n_y <F y , it is judged that the nth blank characteristic of the yth successful element type two-state task is similar to the nth blank characteristic of the new element type two-state task; otherwise, it is judged that the nth blank characteristic of the yth successful element type two-state task is not similar to the nth blank characteristic of the new element type two-state task, and then the adaptive characteristic quantity G n_x of the nth blank characteristic of the xth service personnel is obtained, the adaptive characteristic quantity represents the number of blank characteristics that meet the similarity with the nth blank characteristic of the new element type two-state task in the nth blank characteristic of the Y successful element type two-state task, x=1, 2, …, X is substituted in turn, the adaptive characteristic quantity {G n_1 ,G n_2 ,…,G n_x ,…,G n_X} of the nth blank characteristic of the X service personnel is obtained, and then the adaptive score H n_x of the nth blank characteristic of the xth service personnel is obtained. ； Substitute n = 1, 2, …, N to obtain N fill-in characteristic adaptation scores of the xth service personnel, and further obtain the comprehensive score J of the xth service personnel x , J x is the sum of the N fill-in characteristic adaptation scores of the xth service personnel, substitute x = 1, 2, …, X to obtain the comprehensive score of the X service personnel, and select the service personnel with the highest comprehensive score as the selected service personnel of the new element type task.

5. The intelligent identification method for legal documents according to claim 4, characterized in that: In step S6, after the service of the new element two-state task is completed, if the customer is not satisfied with the new element two-state task, the customer dissatisfaction fill-in feature is called, if the nth fill-in feature is the customer dissatisfaction fill-in feature, the weight of the nth fill-in feature is replaced by α*k n , α is a preset weight amplification coefficient, α>1, and the selected service personnel serves the customer again.

6. An intelligent identification system applied to legal documents, the system being applied to the intelligent identification method of legal documents according to any one of claims 1-5, characterized in that: The system comprises a blank data characteristic extraction module, a service personnel library construction module, a new task adaptation module, a busy degree screening and selection module, a characteristic adaptation highest selection module and a feedback secondary analysis module; The blank data characteristic extraction module is used to specify a format of an element type two form, obtain blank data filled in the element type two form by a client, preprocess and normalize the blank data, and obtain N blank characteristics of an element type two form task; The service personnel library construction module is used to analyze service personnel, call successfully processed element type two form tasks, and establish a service personnel database according to characteristics of the successfully processed element type two form tasks; The new task adaptation module is used to establish a new element type two form preset task when a new element type two form appears, analyze an adaptation degree of the service personnel to the new element type two form preset task, and select adaptive service personnel; The busyness screening selection module is configured to select a selected service personnel for the new element type two-status task according to the number of busy cases of the service personnel when there is an adaptive service personnel for the new element type two-status task; The feature adaptation highest selection module is configured to select a service personnel with the highest adaptive degree as the selected service personnel for the new element type two-status task by comprehensively considering the adaptive degree of the fill-in feature when there is no adaptive service personnel for the new element type two-status task; The feedback secondary analysis module is configured to re-analyze the selected service personnel for the customer service if the customer feedback on the new element type two-status task is not satisfied after the service is completed.

Images