Intelligent form filling method and device

Abstract

The invention provides an intelligent order filling method and device, and relates to the field of artificial intelligence, and the method comprises the steps: receiving a target work order task configured by a user through a task configuration page; obtaining record information corresponding to the target work order task; analyzing the record information to obtain call content information; verifying whether the call content information is analyzed, and if not, calling a large model service to analyze the call content information to obtain work order summary information; and querying the summary information of the work order, sending the queried summary information of the work order to a user side, so that the user side displays the summary information of the work order on an analysis result page, and an operator completes order filling according to a copy control in the analysis result page. According to the invention, filling can be automatically and accurately realized, filling efficiency is improved, and manpower is saved. And meanwhile, the current limiting of the request end can be realized, the use resources of the large model are saved, and the resource waste is avoided.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to an intelligent form filling method and device. Background Art

[0002] In the prior art, when filling out a work order for a current call, the agent needs to look up the historical conversation records on the smart assistant page to complete the work order. When filling out a work order for a call on the same day, the agent needs to manually complete the work order by recalling the call content.

[0003] The filling of work orders in the above scenarios needs to be done manually, which is prone to errors and low efficiency. Summary of the invention

[0004] The present invention is used to solve the problems in the prior art of wasting manpower, being prone to errors and having low efficiency in filling out conversation work orders.

[0005] In order to solve the above technical problems, the first aspect of the present invention provides an intelligent form filling method, which is applied to a server, comprising:

[0006] Receive the target work order task configured by the user through the task configuration page;

[0007] Obtaining the record information corresponding to the target work order task;

[0008] Parsing the recorded information to obtain call content information;

[0009] Verify whether the call content information has been analyzed. If not, call the big model service to analyze the call content information to obtain the work order summary information;

[0010] The work order summary information is sent to the user end, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page.

[0011] As a further embodiment of the present invention, the process of determining the task configuration page includes:

[0012] According to the user's task query instruction, the session task data is obtained and returned to the user end, and the user end generates and displays the task configuration page according to the session task data.

[0013] As a further embodiment of the present invention, after acquiring the session task data according to the user task query instruction, the method further includes:

[0014] Desensitizing the sensitive parameters in the session task data.

[0015] As a further embodiment of the present invention, the intelligent form filling method further includes:

[0016] Obtain the record information of the customer in the target work order task within the most recent preset time period.

[0017] As a further embodiment of the present invention, verifying whether the call content information has been analyzed includes:

[0018] Querying a publication flow table to determine the number of times the call content information is published, wherein the publication flow table records at least a call identifier and a number of times the call content information is published;

[0019] If the number of releases is greater than 1, it is determined that the call content information has been analyzed, and if the number of releases is 0, it is determined that the call content information has not been analyzed.

[0020] As a further embodiment of the present invention, after determining that the number of publications is 0, the process further includes:

[0021] Determine whether there is a call identifier related to the call content information in the processed work order database. If so, add 1 to the number of times the relevant call identifier is published in the publishing flow table. If not, determine that the call content information has not been analyzed.

[0022] As a further embodiment of the present invention, the intelligent work order summary publishing interface is called to verify whether the call content information has been analyzed;

[0023] The user terminal triggers the query control in the task configuration page to call the intelligent work order query interface to send the target work order task to the server terminal. The query control cannot be triggered within a predetermined time period after the intelligent work order query interface is triggered. After the predetermined time period, the query control is enabled to be triggered. A second aspect of the present invention provides an intelligent form filling device, which is applied to the server terminal, comprising:

[0024] A receiving unit, used to receive the target work order task configured by the user through the task configuration page;

[0025] An acquisition unit, used to acquire the record information corresponding to the target work order task;

[0026] A parsing unit, used for parsing the recorded information to obtain call content information;

[0027] A verification unit, used to verify whether the call content information has been analyzed, and if not, call the big model service to analyze the call content information to obtain the work order summary information;

[0028] The query unit is used to send the work order summary information to the user end, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page.

[0029] A third aspect of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any of the above embodiments when executing the computer program.

[0030] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of a computer device, the method described in any of the above embodiments is implemented.

[0031] The intelligent form filling method and device provided by the present invention receives the target work order task configured by the user through the task configuration page; obtains the record information corresponding to the target work order task; parses the record information to obtain the call content information; verifies whether the call content information has been analyzed, if not, calls the large model service to analyze the call content information to obtain the work order summary information; sends the work order summary information to the user end, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page, which can automatically and accurately realize the form filling, improve the efficiency and accuracy of form filling and save manpower. At the same time, for a large number of call scenarios or complex customer service systems, before calling the large model service, it is necessary to limit whether the call content information has been analyzed, which can realize the current limiting of the request end, avoid the number of concurrent calls of the large model, save the use resources of the large model, and avoid resource waste.

[0032] In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 The structure diagram of the intelligent form filling system according to the embodiment of the present invention is shown;

[0035] Figure 2 A flow chart of an intelligent form filling method according to an embodiment of the present invention is shown;

[0036] Figure 3 A schematic diagram of a task configuration page according to an embodiment of the present invention is shown;

[0037] Figure 4 A schematic diagram showing an analysis result page of an embodiment of the present invention is shown;

[0038] Figure 5 The structure diagram of the intelligent form filling device according to the embodiment of the present invention is shown;

[0039] Figure 6 A structural diagram of a computer device according to an embodiment of the present invention is shown.

[0040] Description of the accompanying symbols:

[0041] 101. User end;

[0042] 102. Server;

[0043] 301. Query control;

[0044] 302. Display area;

[0045] 303. Query condition setting control;

[0046] 401, display area;

[0047] 402. Operation controls;

[0048] 501, receiving unit;

[0049] 502. Acquisition unit;

[0050] 503, parsing unit;

[0051] 504. Verification unit;

[0052] 505, query unit;

[0053] 602. Computer equipment;

[0054] 604, processor;

[0055] 606. Memory;

[0056] 608, driving mechanism;

[0057] 610, input / output module;

[0058] 612. Input devices;

[0059] 614. Output device;

[0060] 616. Presentation equipment;

[0061] 618. Graphical user interface;

[0062] 620, network interface;

[0063] 622, communication link;

[0064] 624. Communication bus. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0067] This specification provides method operation steps as described in the embodiments or flow charts, but more or fewer operation steps may be included based on routine or non-creative work. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the system or device product is executed in practice, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel.

[0068] It should be noted that the intelligent form filling method and device of the present invention are applicable to various scenarios with manual customer service, and the present invention does not limit the application field of the intelligent form filling method and device.

[0069] It should be noted that the user information (including but not limited to user device information, user personal information, call content information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the acquisition, transmission, storage, use and processing of relevant data shall comply with the relevant laws, regulations and standards of relevant countries and regions.

[0070] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0071] In the prior art, after talking to a customer, the agent will record the summary of the conversation into a work order. Existing work orders are all filled out manually by the agent. This method wastes manpower, is prone to errors, and is inefficient. In order to solve this technical problem, the present invention provides an intelligent form filling system, such as Figure 1 As shown, it includes a client 101 and a server 102 .

[0072] The user terminal 101 can be a desktop computer, a tablet computer, a laptop computer, a smart phone, a digital assistant, a smart wearable device, etc. Among them, the smart wearable device can include a smart bracelet, a smart watch, smart glasses, a smart helmet, etc. Of course, the client is not limited to the above-mentioned electronic device with a certain entity, it can also be a software running in the above-mentioned electronic device. Specifically, the smart form filling system app can be installed on the user terminal 101, or the user terminal 101 is the smart form filling system app. After the user logs in to the smart form filling system, the task configuration page will be displayed, and the target work order task will be entered through the task configuration page, and the target work order task will be sent to the server 102; it also receives and displays the work order summary information sent by the server 102. Specifically, the work order summary information is displayed on the analysis result page.

[0073] In some implementations, the task configuration page is as follows: Figure 3 As shown, the task configuration page includes a query control 301, a display area 302, and a query condition setting control 303, wherein the query condition setting control 303 includes but is not limited to a user field setting control and a caller number setting control, and may also include a date setting control, a SAP setting control, etc. The user completes the setting of the query condition by inputting information in the corresponding setting control, and sends the query condition to the server 102 through the query control 301. The server 102 queries all the session task data that meet the condition according to the query condition, and feeds back to the user end 101. The user end 101 displays the session task data fed back by the server 102 in the display area 302 in the form of a list. Each task displayed in the display area 302 has a selection control. The user completes the configuration of the target work order task by triggering the selection control, and sends the target work order task to the server 102 through the query control 301.

[0074] The analysis result page is as follows Figure 4 As shown, it includes a display area 401 and an operation control 402, wherein the operation control 402 includes a copy control and a close control. The display area 401 displays the work order summary information of the target work order task configured by the user. The user completes the copying of the work order summary information in the display area 401 by triggering the copy control, and closes the analysis result page by closing the control.

[0075] In detail, the work order summary information includes: product information, activity information, problem information, etc. For example, a customer calls to inquire about a certain activity of ****** product, and the customer says that he has used it but cannot receive it, and asks to inquire about the reason.

[0076] The server end 102 is used to receive the target work order task configured by the user through the task configuration page; obtain the record information corresponding to the target work order task; parse the record information to obtain the call content information; verify whether the call content information has been analyzed, if not, call the large model service to analyze the call content information to obtain the work order summary information; send the work order summary information to the user end 101, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page.

[0077] This embodiment can automatically and accurately fill out forms, improve form filling efficiency and save manpower. At the same time, for a large number of call scenarios or complex customer service systems, before calling the big model service, it is necessary to limit whether the call content information has been analyzed, which can achieve current limiting on the request side, avoid the number of concurrent calls to the big model, save the use of big model resources, and avoid resource waste.

[0078] In one embodiment of the present invention, Figure 2 As shown, an intelligent form filling method is also provided, including:

[0079] Step 201: Receive the target work order task configured by the user through the task configuration page.

[0080] The task configuration page is as follows: Figure 3 As shown, the user inputs the query condition in the query condition setting control 303, and sends the query condition to the server 102 through the query control 301. The server 102 searches for the session task data that meets the query condition and displays it in the display area 302 of the task configuration page. Each session task data corresponds to a call. The session task data includes but is not limited to: caller number, customer name, card number, call time, user number (SAP number) and call identifier (such as session ID).

[0081] The target work order task is obtained by the user from the work order tasks displayed in the display area. In some implementations, all fields of the target work order task are spliced, the maximum number of spliced ​​sessions is a preset amount, such as 1000, and the maximum field length is a preset field, such as 30000 fields. The user sends the target work order task to the server 102 by triggering the query control 301.

[0082] During specific implementation, in order to distinguish between sending query conditions and sending operations of target work order tasks, a smart work order summary control may also be set. The user sends the query conditions to the server 102 by triggering the query control 301, and sends the target work order tasks to the server 102 by triggering the smart work order summary control.

[0083] Step 202: Obtain record information corresponding to the target work order task.

[0084] The record information corresponding to the work order task includes voice information, caller number, customer name, card number, call time, user number (SAP number) and call ID. In the specific implementation, the record information is queried through the sql component.

[0085] Step 203: parse the record information to obtain call content information.

[0086] The call content information in this step is text information, that is, the voice information is converted into text information. The specific conversion algorithm can refer to the existing technology and will not be described in detail here.

[0087] Step 204, verify whether the call content information has been analyzed, if not, call the big model service to analyze the call content information to obtain the work order summary information.

[0088] In detail, the database of the intelligent form filling system records a release flow table, which records at least a call identifier and a release count. The call identifier is generated during a call and is used to uniquely locate the call. The release count is used to indicate the number of times the call content of the corresponding call identifier calls the large model. If it is less than 1, it means that the large model has not been called and the call content information has not been analyzed. If it is equal to or greater than 1, it means that the large model has been called and the call content information has been analyzed.

[0089] In some implementations, the publishing flow table records: table field ID (primary key id), publisher (SAP), publishing time (PUBLISH_DATE), number of model usages (PUBLISH_COUNT), and call identifier (CONNECT_ID).

[0090] After calling the big model for a certain call content information, the number of publications of the related call content information is inserted or updated in the publishing flow table as 1, the updated publishing time is the current system time, and the updated publisher is the current user.

[0091] The large model used in the present invention can be a large model obtained by training based on the technology of the large model in the prior art and combining it with the application scenario knowledge base. The present invention does not limit the large model structure, algorithm logic and training process.

[0092] When calling the big model, in addition to entering the call content information, you can also enter the required information (such as call type), so that the big model can accurately obtain the work order summary information.

[0093] In specific implementation, in order to prevent the customer service from completing the work order for the call content during the call, when it is determined that the number of releases is less than 1 (that is, the number of releases is 0, or there is no release number), it also includes:

[0094] Determine whether there is a call identifier related to the call content information in the processed work order database. If so, the work order filling of the relevant call content has been completed, and the number of releases of the relevant call identifier in the release flow table is increased by 1. If not, it is determined that the call content information has not been analyzed. The processed work order database stores session related information for which the work order filling has been completed.

[0095] The work order summary information includes: product information, activity information, problem information, etc.

[0096] In some implementations, steps 202 to 204 are implemented by an intelligent work order summary publishing interface. After the intelligent work order summary publishing interface completes the call, it returns the front-end transaction success information.

[0097] Step 205, the work order summary information is sent to the user end, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page.

[0098] This embodiment is suitable for scenarios where the throughput of a large model is low and a large number of calls are not supported. By analyzing whether the call content information has been analyzed before calling the large model, it is possible to avoid wasting model resources by repeated use.

[0099] In one embodiment of the present invention, the user terminal triggers the query control in the task configuration page to call the smart work order summary query interface to send the target work order task to the server. In some implementations, in order to avoid frequent access to large models, after the smart work order summary publishing interface is called for a predetermined time period, the smart work order query interface is called to query the work order summary information. Specifically, the query control cannot be triggered within a predetermined time period after the smart work order query interface is triggered. After the predetermined time period, the query control is enabled to be triggered, that is, the query control can be triggered.

[0100] In some implementations, the intelligent work order summary query interface completes the query of the work order summary information by sending the fields SAP number, line time, session id, encrypted mobile phone number, and event id. Call the transaction to query the work order summary content. If the query is successful, the query result is displayed in the form of a pop-up window on the user side; if the query fails, the countdown for the predetermined time period is started again (for example, a 5-second countdown). When the countdown reaches 0, the intelligent work order summary query interface is called again. If the query is successful, the query result is displayed in the form of a pop-up window on the user side. If the query still fails, the query transaction will not be initiated, and a pop-up window will pop up on the user side to prompt "No matching results found".

[0101] In one embodiment of the present invention, the process of determining the task configuration page includes:

[0102] According to the user's task query instruction, the session task data is obtained and returned to the user end, and the user end generates and displays the task configuration page according to the session task data.

[0103] In one embodiment of the present invention, after acquiring the session task data according to the user task query instruction, the method further includes: performing desensitization processing on sensitive parameters in the session task data.

[0104] The session task data includes the caller number, customer name, card number, call time, user number (SAP number) and call identification (such as session ID). For the card number, only the first and last digits can be displayed, for example, the first 6 digits + * (actual number of digits) + the last 4 digits can be displayed, such as 622566******6666. For another example, the ID card number displays the first 12 digits and masks the last 6 digits, such as 123456789123******; the passport number retains one letter and the last 3 digits, and the rest are replaced by *, such as G*****123, etc.

[0105] This embodiment can ensure user data security by desensitizing session task data.

[0106] In one embodiment of the present invention, in addition to obtaining the record information corresponding to the target work order task, the above step 202 also obtains the record information of the customer in the target work order task within the most recent preset time period.

[0107] The predetermined time period is, for example, 30 minutes, which can be preset and is not specifically limited in the present invention.

[0108] This embodiment combines the conversation contents of different conversation IDs of the same customer within a predetermined time period and sends them to the big model side, so that the work order summary information can be generated by combining the customer's multi-conversation contents, so that the generated work order summary information can better reflect the customer's demands.

[0109] In one embodiment of the present invention, after obtaining the record information corresponding to the target work order task and the record information within the customer preset time period in the target work order task, the record information is also processed by data cleaning, screening, integration, etc., so as to obtain data that meets the requirements of the large model, thereby improving the recognition accuracy of the large model.

[0110] In one embodiment of the present invention, after the big model is called successfully, the call time, transaction code, operator, and big model return result are recorded in a report to facilitate the user to analyze the big model usage rate and further optimize the big model, such as optimizing the time interval for calling the big model.

[0111] Based on the same inventive concept, the present invention also provides an intelligent form filling device, as described in the following embodiments. Since the principle of solving the problem by the intelligent form filling device is similar to that of the intelligent form filling method, the implementation of the intelligent form filling device can refer to the intelligent form filling method, and the repeated parts will not be repeated.

[0112] Specifically, Figure 5 As shown, the intelligent form filling device includes:

[0113] The receiving unit 501 is used to receive the target work order task configured by the user through the task configuration page.

[0114] The acquisition unit 502 is used to acquire the record information corresponding to the target work order task.

[0115] The parsing unit 503 is used to parse the record information to obtain call content information.

[0116] The verification unit 504 is used to verify whether the call content information has been analyzed. If not, the large model service is called to analyze the call content information to obtain the work order summary information.

[0117] The query unit 505 is used to send the work order summary information to the user end, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page.

[0118] This embodiment can automatically and accurately fill out forms, improve form filling efficiency and save manpower. At the same time, for a large number of call scenarios or complex customer service systems, before calling the big model service, it is necessary to limit whether the call content information has been analyzed, which can achieve current limiting on the request side, avoid the number of concurrent calls to the big model, save the use of big model resources, avoid resource waste, and improve the stability of the system.

[0119] In one embodiment of the present invention, a computer device is provided, such as Figure 6As shown, the computer device 602 may include one or more processors 604, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 602 may also include any memory 606, which is used to store any kind of information such as code, settings, data, etc. Non-limitingly, for example, the memory 606 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent a fixed or removable component of the computer device 602. In one case, when the processor 604 executes an associated instruction stored in any memory or a combination of memories, the computer device 602 may perform any operation of the associated instruction. The computer device 602 also includes one or more drive mechanisms 608 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0120] The computer device 602 may also include an input / output module 610 (I / O) for receiving various inputs (via input device 612) and for providing various outputs (via output device 614). A specific output mechanism may include a presentation device 616 and an associated graphical user interface 618 (GUI). In other embodiments, the input / output module 610 (I / O), input device 612, and output device 614 may not be included, and the computer device 602 may be used as a computer device in a network. The computer device 602 may also include one or more network interfaces 620 for exchanging data with other devices via one or more communication links 622. One or more communication buses 624 couple the components described above together.

[0121] The communication link 622 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 622 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0122] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are executed.

[0123] An embodiment of the present invention further provides a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to execute the method described in any of the aforementioned embodiments.

[0124] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0125] It should also be understood that in the embodiments of the present invention, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0126] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0128] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0129] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0130] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0132] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An intelligent form filling method, characterized in that: Applied to the server, including: Receive the target work order task configured by the user through the task configuration page; Obtaining the record information corresponding to the target work order task; Parsing the recorded information to obtain call content information; Verify whether the call content information has been analyzed. If not, call the big model service to analyze the call content information to obtain the work order summary information; The work order summary information is sent to the user end, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page.

2. The method according to claim 1, characterized in that The process of determining the task configuration page includes: According to the user's task query instruction, the session task data is obtained and returned to the user end, and the user end generates and displays the task configuration page according to the session task data.

3. The method according to claim 2, characterized in that After acquiring the session task data according to the user task query instruction, the method further includes: Desensitizing the sensitive parameters in the session task data.

4. The method according to claim 1, characterized in that Also includes: Obtain the record information of the customer in the target work order task within the most recent preset time period.

5. The method according to claim 1, characterized in that Verify whether the call content information has been analyzed, including: Querying a publication flow table to determine the number of times the call content information is published, wherein the publication flow table records at least a call identifier and a number of times the call content information is published; If the number of releases is greater than 1, it is determined that the call content information has been analyzed, and if the number of releases is 0, it is determined that the call content information has not been analyzed.

6. The method according to claim 5, characterized in that After confirming that the number of releases is 0, it also includes: Determine whether there is a call identifier related to the call content information in the processed work order database. If so, add 1 to the number of times the relevant call identifier is published in the publishing flow table. If not, determine that the call content information has not been analyzed.

7. The method according to claim 1, characterized in that Calling the intelligent work order summary publishing interface to verify whether the call content information has been analyzed; The user terminal triggers the query control in the task configuration page to call the smart work order query interface to send the target work order task to the server terminal. The query control cannot be triggered within a predetermined time period after the smart work order query interface is triggered. After the predetermined time period, the query control is enabled to be triggered.

8. An intelligent form filling device, characterized in that: Applied to the server, including: A receiving unit, used to receive the target work order task configured by the user through the task configuration page; An acquisition unit, used to acquire the record information corresponding to the target work order task; A parsing unit, used for parsing the recorded information to obtain call content information; A verification unit, used to verify whether the call content information has been analyzed, and if not, call the big model service to analyze the call content information to obtain the work order summary information; The query unit is used to send the work order summary information to the user end, so that the user end displays the work order summary information on the analysis result page, and the operator completes the form filling according to the copy control in the analysis result page.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor of a computer device, the method according to any one of claims 1 to 7 is implemented.

Images