A data processing system for workload identification in feasibility study texts

Abstract

The present invention discloses a data processing system for the workload recognition of feasibility study texts, which relates to the technical field of text recognition and processing. The target object is obtained through the object acquisition unit, and then the target object is analyzed in the same direction by means of the same-direction search unit. A number of feasibility study text data are retrieved according to the keywords of the target object, and then all the comparison documents are determined according to the similarity between the feasibility study text data and the target object. Then, the comparison documents and the target object are compared by means of the latch unit to automatically confirm the data, identify all the abnormal data, and remind the staff to review. At the same time, the construction period can also be automatically identified, and the monitoring time points can be identified according to the stage progress. The present invention is simple and effective and easy to use.

Description

Technical Field

[0001] The present invention belongs to the technical field of feasibility study text recognition, and specifically relates to a data processing system for recognizing the workload of feasibility study text. Background Art

[0002] The patent with the publication number CN115331237A discloses a training method of a text recognition model, a text recognition method, a device and equipment. The training method of the text recognition model includes: obtaining a first text recognition model; training the first text recognition model, and when the training process of the first text recognition model reaches a first training condition, reducing the number of network layers in the decoding module to a target number to obtain a second text recognition model; training the second text recognition model, and when the training process of the second text recognition model reaches a second training condition, replacing the encoding module in the second text recognition model with a lightweight encoding module to obtain a third text recognition model; training the third text recognition model, and when the training process of the third text recognition model reaches a third training condition, obtaining the trained text recognition model. The present invention adjusts and trains the text recognition model multiple times, taking into account both the accuracy and size of the model, and improving the applicable range of the model.

[0003] This patent provides a reasonable text recognition model. However, for some special feasibility study texts, how to perform text discrimination based on text recognition, and at the same time be able to recognize the content in the text and automatically track it. Based on this, a solution is provided herein. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art;

[0005] For this purpose, the present invention proposes a data processing system for recognizing the workload of feasibility study text, including:

[0006] An object acquisition unit for acquiring a target object and transmitting the target object to a same-direction search unit. The same-direction search unit receives the target object transmitted by the object acquisition unit, performs a same-direction analysis on the target object, retrieves a number of feasibility study text data according to the keywords of the target object, and then determines all comparison documents according to the similarity between the feasibility study text data and the target object;

[0007] The same-direction search unit is used to transmit the comparison document and the target object to a latch unit. The latch unit receives the comparison document and the target object transmitted by the same-direction search unit and automatically performs data confirmation. The specific method of data confirmation is as follows:

[0008] S1: Obtain all the numerical data in the target object, mark it as a numerical target, and then automatically obtain the header target of the numerical target;

[0009] S2: Obtain the header content consistent with the header label in all compared documents, mark it as the comparison header, obtain the data after the comparison header, and mark it as the comparison data; obtain several sets of comparison data and their corresponding comparison headers;

[0010] S3: then the comparison mark that is consistent with the header mark is regarded as a combination, and the corresponding numerical mark and the comparison data are marked as a comparison combination;

[0011] S4: Obtain the range from the minimum value to the maximum value of all the comparison data in the comparison combination, and mark it as the comparison combination range;

[0012] S5: When the obtained numerical value is not within the comparison combination range, the header of the corresponding numerical value is marked as an abnormal value, otherwise no processing is performed;

[0013] S6: Get the number of abnormal labels, divide it by the number of all header labels, and get the abnormal proportion;

[0014] S7: When the abnormality ratio does not exceed the set ratio, a verification signal is generated;

[0015] S8: When a verification signal is generated, staff are required to verify the data.

[0016] Furthermore, the subject matter is the corresponding feasibility study report.

[0017] Furthermore, the specific method of same-direction analysis is as follows:

[0018] Get the target object, get the title of the target object, retrieve all feasibility study text data containing relevant titles, and mark them as related data. The specific retrieval method is:

[0019] The keywords in the target object are obtained. The keywords are first segmented by the target object to obtain several segmented words. Then the number of occurrences of each segmented word is automatically obtained. The numbers of occurrences are sorted from large to small, and the top five are marked as keywords.

[0020] Search the feasibility study text database based on keywords and mark all documents containing all keywords as related documents;

[0021] After that, all the related documents are compared with the target object one by one to obtain the similarity between each related document and the target object, and those with similarity exceeding X1 are marked as comparison documents; here X1 is a preset value.

[0022] Further, the latching unit is used to transmit the verification signal to the processor. When the processor receives the verification signal transmitted by the latching unit, it will automatically drive the display unit to display "The data in the current feasibility study text is abnormal. Please verify carefully.";

[0023] It further includes a management unit, which is communicatively connected to the processor and is used to input all preset values.

[0024] Further, the latching unit is also used to transmit the target object without generating a verification signal to the processor. The processor automatically extracts the sub - phases and phase nodes in the corresponding target object. The sub - phase refers to several engineering phases that need to be experienced to complete the corresponding target object, and the phase node is the time node when the corresponding sub - phase is completed;

[0025] The processor is used to transmit the sub - phases and phase nodes to the key interception unit. The key interception unit receives the sub - phases and phase nodes transmitted by the processor. At the start of the project, the key interception unit will automatically form a project progress schedule according to the sub - phases and phase nodes. The key interception unit is used to transmit the project progress schedule to the proxy supervision unit. When the proxy supervision unit receives the project recommendation schedule, it will automatically supervise, and when the corresponding time expires, it will automatically send a warning signal and transmit the warning signal to the processor. The processor is used to transmit the warning signal to the display unit. When the display unit receives the warning signal transmitted by the processor, it will automatically display "The current progress is abnormal. Please verify in time."

[0026] Further, the set ratio in step S7 is within a preset value range.

[0027] Further, the method for obtaining the set ratio in step S7 is as follows:

[0028] Obtain all the header targets and value targets;

[0029] Then, arbitrarily select one from all the header targets and change the value of the corresponding value target;

[0030] Then, through the confirmation of the staff, determine the values of the value targets corresponding to the other header targets that need to be modified accordingly, and mark them as a set value; the difference between the modified value and the original value here exceeds X2, where X2 is a preset value;

[0031] Then, select the value target corresponding to any next header target and repeat the above process until all the header targets have been modified. Obtain all the set values, mark the minimum value of all the set values as the lower limit value, mark the range smaller than the lower limit value as the set ratio, compare the abnormal ratio with the set ratio, and generate a verification signal when the abnormal ratio is less than the set ratio.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention obtains the target object through the object acquisition unit, and then uses the same-direction search unit to perform same-direction analysis on the target object, retrieves a number of feasibility study text data according to the keywords of the target object, and then determines all the comparison documents according to the similarity between the feasibility study text data and the target object;

[0034] Afterwards, the latch unit is used to compare the document and the target object, automatically confirm the data, confirm all abnormal data, and remind the staff to review. At the same time, the construction period can be automatically identified, and the monitoring time point can be identified according to the stage progress. The present invention is simple, effective, and easy to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0036] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0037] See also Figure 1 The present application provides a data processing system for identifying the workload of feasibility study texts, including:

[0038] An object acquisition unit, a same-direction search unit, a latch unit, a management unit, a processor, a display unit, a key interception unit, and a substitute direction supervision unit;

[0039] The object acquisition unit is used to acquire the target object, which is the corresponding feasibility study report, that is, the feasibility study text mentioned in this article, and transmit the target object to the same-direction search unit. The same-direction search unit receives the target object transmitted by the object acquisition unit and performs a same-direction analysis on the target object. The specific method of the same-direction analysis is as follows:

[0040] Get the target object, get the title of the target object, retrieve all feasibility study text data containing relevant titles, and mark them as related data, which are actually the target objects with the same name. Of course, you can also use the following method to search here. The search method is:

[0041] The keywords in the target object are obtained. The keywords are first segmented by the target object to obtain several segmented words. Then the number of occurrences of each segmented word is automatically obtained. The numbers of occurrences are sorted from large to small, and the top five are marked as keywords.

[0042] Retrieve in the feasibility study text database according to the keywords, and mark all the documents containing all the keywords as associated documents;

[0043] After that, compare all the associated documents with the target object one by one to obtain the similarity between each associated document and the target object, and mark the documents with similarity exceeding X1 as comparison documents; here, X1 is a preset value, which can generally be set to 0.8;

[0044] The co-directional search unit is used to transmit the comparison documents and the target object to the latch unit. The latch unit receives the comparison documents and the target object transmitted by the co-directional search unit and automatically conducts data confirmation. The specific method of data confirmation is as follows:

[0045] S1: Obtain all the numerical data in the target object, mark it as the numerical target, and then automatically obtain the header target of the numerical target;

[0046] S2: Obtain the header content in all the comparison documents that is the same as the header target, mark it as the comparison header, and obtain the data after the comparison header, mark it as the comparison data; obtain several pieces of comparison data and their corresponding comparison headers;

[0047] S3: Then take the comparison targets that are the same as the header target as a combination, and mark the corresponding numerical target and the comparison data as a comparison combination;

[0048] S4: Obtain the range from the minimum value to the maximum value of all the comparison data in the comparison combination, and mark it as the comparison combination range;

[0049] S5: When the numerical target is not within the comparison combination range, mark the header target corresponding to the numerical target as an abnormal target, otherwise do not process;

[0050] S6: Obtain the number of abnormal targets, divide it by the number of all header targets, and obtain the abnormal proportion;

[0051] S7: When the abnormal proportion does not exceed the set proportion, generate a verification signal. Here, the set proportion is a preset numerical range; because when the numerical target corresponding to any header target changes, the numerical targets corresponding to several other header targets need to change, so the abnormal proportion here must be divided by a reasonable range;

[0052] S8: When a verification signal is generated, the staff is required to verify the data;

[0053] The latch unit is used to transmit the verification signal to the processor. When the processor receives the verification signal transmitted by the latch unit, it will automatically drive the display unit to display "The data in the current feasibility study text is abnormal, please verify carefully";

[0054] It further includes a management unit, which is communicatively connected to the processor and is used for inputting all preset values;

[0055] As Embodiment 2 of the present invention, on the basis of Embodiment 1, the latching unit is further used to transmit the target object without a verification signal to the processor, and the processor automatically extracts the sub - phases and phase nodes in the corresponding target object. The sub - phase refers to several engineering phases that need to be experienced to complete the corresponding target object, and the phase node is the time node when the corresponding sub - phase is completed;

[0056] The processor is used to transmit the sub - phases and phase nodes to the key interception unit. The key interception unit receives the sub - phases and phase nodes transmitted by the processor. At the start of the project, the key interception unit will automatically form a project progress schedule according to the sub - phases and phase nodes. The project progress schedule is a time record table of what project should be carried out at what time; the key interception unit is used to transmit the project progress schedule to the proxy supervision unit. When the proxy supervision unit receives the project recommendation schedule, it will automatically supervise, and when the corresponding time expires, it will automatically send a warning signal and transmit the warning signal to the processor. The processor is used to transmit the warning signal to the display unit. When the display unit receives the warning signal transmitted by the processor, it will automatically display "The current progress is abnormal. Please verify in time."

[0057] As Embodiment 3 of the present invention, the method for obtaining the set ratio in step S7 in Embodiment 1 is different. The method for obtaining the set ratio in this embodiment is as follows:

[0058] Obtain all the header targets and value targets;

[0059] Then, randomly select one from all the header targets and change the value of the corresponding value target;

[0060] Then, have the staff confirm the values of the value targets corresponding to the other header targets that need to be modified accordingly, and mark them as a set value; the difference between the modified value and the original value here exceeds X2, and X2 is a preset value;

[0061] Then, select the value target corresponding to any next header target and repeat the above process until the modification processing of all the header targets is completed to obtain all the set values. Mark the minimum value of all the set values as the lower limit value, mark the range less than the lower limit value as the set ratio, compare the abnormal ratio with the set ratio, and generate a verification signal when the abnormal ratio is less than the set ratio;

[0062] As Embodiment 4 of the present invention, the technical solution of this embodiment lies in integrating Embodiments 1 to 3 for implementation.

[0063] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A data processing system for identifying the workload of a feasibility study text, characterized in that, include: The object acquisition unit is used to acquire the target object and transmit the target object to the same-direction search unit. The same-direction search unit receives the target object transmitted by the object acquisition unit, performs a same-direction analysis on the target object, retrieves a number of feasibility study text data according to the keywords of the target object, and then determines all the comparison documents according to the similarity between the feasibility study text data and the target object; The same-direction search unit is used to transmit the comparison document and the target object to the latch unit. The latch unit receives the comparison document and the target object transmitted by the same-direction search unit and automatically performs data confirmation. The specific method of data confirmation is: S1: Get all the numerical data in the target object, mark it as a numerical target, and then automatically get the header target of the numerical target; S2: Obtain the header content consistent with the header label in all compared documents, mark it as the comparison header, obtain the data after the comparison header, and mark it as the comparison data; obtain several sets of comparison data and their corresponding comparison headers; S3: then the comparison mark that is consistent with the header mark is regarded as a combination, and the corresponding numerical mark and the comparison data are marked as a comparison combination; S4: Obtain the range from the minimum value to the maximum value of all the comparison data in the comparison combination, and mark it as the comparison combination range; S5: When the obtained numerical value is not within the comparison combination range, the header of the corresponding numerical value is marked as an abnormal value, otherwise no processing is performed; S6: Get the number of abnormal labels, divide it by the number of all header labels, and get the abnormal proportion; S7: When the abnormality ratio does not exceed the set ratio, a verification signal is generated; S8: When a verification signal is generated, staff are required to verify the data.

2. The data processing system for identifying the workload of a feasibility study text according to claim 1, wherein, The target object is the corresponding feasibility study report.

3. A data processing system for identifying the workload of a feasibility study text according to claim 1, characterized in that, The specific method of same-direction analysis is: Get the target object, get the title of the target object, retrieve all feasibility study text data containing relevant titles, and mark them as related data. The specific retrieval method is: The keywords in the target object are obtained. The keywords are first segmented by the target object to obtain several segmented words. Then the number of occurrences of each segmented word is automatically obtained. The numbers of occurrences are sorted from large to small, and the top five are marked as keywords. Search the feasibility study text database based on keywords and mark all documents containing all keywords as related documents; After that, all the related documents are compared with the target object one by one to obtain the similarity between each related document and the target object, and those with similarity exceeding X1 are marked as comparison documents; here X1 is a preset value.

4. A data processing system for recognizing the workload of a feasibility study text according to claim 1, characterized in that The latch unit is used to transmit the verification signal to the processor. When the processor receives the verification signal transmitted by the latch unit, it will automatically drive the display unit to display "The data in the current feasibility study text is abnormal, please verify carefully"; It also includes a management unit, which is connected to the processor for inputting all preset values.

5. A data processing system for identifying the workload of a feasibility study text according to claim 1, characterized in that, The latch unit is also used to transfer the target object without a verification signal to the processor, and the processor automatically extracts the sub - phases and phase nodes within the corresponding target object. The sub - phase refers to several engineering phases that need to be experienced to complete the corresponding target object, and the phase node is the time node when the corresponding sub - phase is completed; The processor is used to transfer the sub - phases and phase nodes to the key interception unit. The key interception unit receives the sub - phases and phase nodes transferred by the processor. At the start of the project, the key interception unit will automatically form a project progress schedule according to the sub - phases and phase nodes. The key interception unit is used to transfer the project progress schedule to the proxy supervision unit. When the proxy supervision unit receives the project recommendation schedule, it will automatically supervise, and when the corresponding time expires, it will automatically send out a warning signal and transfer the warning signal to the processor. The processor is used to transfer the warning signal to the display unit. When the display unit receives the warning signal transferred by the processor, it will automatically display "The current progress is abnormal. Please verify it in time." 6. The data processing system for identifying the workload of feasibility study texts according to claim 1, characterized in that, The set ratio in step S7 is within a preset numerical range.

7. A data processing system for identifying the workload of a feasibility study text according to claim 1, characterized in that, The method for obtaining the set ratio in step S7 is as follows: Obtain all the header targets and value targets; Then, randomly select one from all the header targets and change the value of the corresponding value target; After that, confirm with the staff the values of the value targets corresponding to the other header targets that need to be modified accordingly, and mark them as a set value. Here, the difference between the modified value and the original value exceeds X2, where X2 is a preset value; Then, select the value target corresponding to any next header target and repeat the above process until the modification process for all header targets is completed, obtaining all the set values. Mark the minimum value of all the set values as the lower limit value, mark the range less than the lower limit value as the set ratio, and compare the abnormal ratio with the set ratio. When the abnormal ratio is less than the set ratio, a verification signal is generated.

Images