TWM581227U - Voice object search system - Google Patents

Abstract

The present invention provides a voice object search system, which includes a database, a voice module, and a search module. The database is configured to store a plurality of objects, wherein each of the objects includes at least one object feature; the voice module is configured to receive the first voice object condition and utilize the voice recognition phrase relative to the search context in accordance with the search context, Converting the first utterance condition to a first item condition string; and the search module is configured to find the at least one object trait and the first object condition string and the at least one object feature An object condition string matches the plurality of objects in a predetermined condition to produce a search result including a specific number of the plurality of objects.

Description

Voice object search system

This creation is about a voice object search system, especially a search system that finds a voice object that matches each other in a predetermined condition based on a voice object search condition string.

There are many considerations for purchasing real estate, such as: price, location, public ratio, number of pings, life function, type of object, etc. The common real estate search method is based on the above-mentioned aspects as a condition for customers to search, for example, the total price of the search is lower than one. Tens of thousands of items or objects in the second room and one hall. However, the results of the above-mentioned objects displayed by the customer are still very messy, and it still takes a lot of effort and spirit to browse and filter each object one by one. The usual retrieval method cannot fully satisfy the customer's demand for purchase considerations.

Moreover, many customers currently purchase real estate is not a single consideration of the conditions of the object itself, but the priority is whether the object in which the object is located meets its preferences or needs, that is, to find a good house first The concept of finding good objects has gradually become a trend. However, the existing real estate search methods are still carried out under the conditions of the objects themselves, or they can only be queried to find out which objects in an administrative area, and must be selected one by one to enter each object classification. Knowing the conditions of the object (such as the age of the house, the total price band, etc.), so that the customer needs to spend more time to find the satisfactory items, the room owner can not smoothly provide the information of the items sold by the system to the customer.

In addition, with the development of voice technology, speech recognition The counts are also introduced one by one in the demand for real estate transactions, but the speech recognition rate has always been one of the most troublesome issues. If the results are often identified, it is always what the user thinks. After a long time, the user will no longer use the speech recognition to search.

For the sake of his position, the applicant has invented the creation of the "Voice Object Search System" to improve the above-mentioned deficiencies in view of the lack of prior art.

Therefore, there is a need for a voice object search system that overcomes the problems of the prior art. In order to achieve the above object, the present invention provides a voice object search system, which includes a database, a voice module, and a search module. The database is configured to store a plurality of objects, wherein each of the objects includes at least an object feature; the voice module is configured to receive the first voice object condition and, in accordance with the search context, utilize a speech recognition phrase relative to the search context, Converting the first utterance condition to a first object condition string; and the search module is configured to find the at least object feature and the first object condition by comparing the first object condition string with the at least object feature The string matches the plurality of objects in a predetermined condition to produce a search result comprising a specific number of the plurality of objects.

In order to reduce the speech recognition error rate, the authoring system will convert the speech object condition into an object condition string according to the search context, using the speech recognition phrase relative to the search context, and then perform the search process.

The voice object search system provided by this creation can fully satisfy the needs of customers in real estate purchase, that is, the voice object search system of this creation searches for the object-first search method, and the user inputs the demand for the house type such as the object. After the system presents the result of the collection of objects, the user can first select the object that is satisfactory, and then browse the objects for sale, because the object can often reflect the quality of life of the object. Living conditions, so the object-first search method can effectively enable the room owner to provide the information of the goods it sells to the customer through the system, thereby enhancing the chances of the two parties.

10‧‧‧Voice Object Search System

101‧‧‧User side

105‧‧‧Database

106‧‧‧Multiple objects

110‧‧‧Voice Module

120‧‧‧Search Module

130‧‧‧Output module

106A‧‧‧ Objects

106B‧‧‧ Objects

A01, A02, A03, A04‧‧‧ object features

S01, S02‧‧‧Saleable items

20‧‧‧System Search Page

205‧‧‧Search type options

206‧‧‧Search Type Options

210‧‧‧Search conditions

211‧‧‧Search conditions

215‧‧‧Search button

220‧‧‧Map block

221‧‧‧ mark

222‧‧‧ mark

230‧‧‧Search results block

231‧‧‧Project

232‧‧‧Project

30‧‧‧Executive process

Steps S301, S302, S303, S304, S305, S306, S307, S308‧‧

1 is a schematic diagram showing a voice object search system of the present creation; FIG. 2 is a schematic diagram showing a database of the creation; FIG. 3 is a schematic diagram showing a system search page of the creation; and FIG. 4 is a diagram showing the creation of the present Schematic diagram of the system search page; Figure 5 is a schematic diagram showing the system search page of the creation;

The present invention will be fully understood by the following examples, which can be accomplished by those skilled in the art, and the present invention can be widely practiced in other embodiments. That is, the implementation of the present invention is not limited to the implementation of the following embodiments, but should be based on the scope of the patent application proposed by the present invention.

Please refer to Figure 1 for a schematic diagram of the voice object search system of the present creation. In FIG. 1 , the voice object search system 10 includes a database 105, a voice module 110, a search module 120, and an output module 130. The database 105 stores a plurality of objects 106, and the plurality of objects 106 have at least one object. Features (detailed in Figure 2). The voice object search system 10 has a user terminal 101. The voice module 110 receives the first voice object condition about the object feature sent by the user terminal 101, and uses the voice recognition phrase relative to the search context according to the search scenario. The first speech object condition is converted into a first object condition string. Among them, the search situation includes different situations such as renting a house, buying a house, selling a house, etc., and in different search situations, there will be relative speech recognition phrases. Identification, the generated first object condition string also belongs to the speech recognition phrase, which reduces erroneous speech recognition. Further, it is also possible to incorporate learning functions.

For example, in the search situation of home purchase and sale, the same first voice object condition, such as double connection, the search situation of the purchase house is more likely to find the objects around the Shuanglian MRT station, so the first object condition The string comparison may be a Shuanglian MRT station, and the search situation in the sale of homes is more likely to be looking for objects around Shuanglian Street. Therefore, the first object condition string may be double-street instead of Shuanglianjie. Transport station.

After receiving the first object condition string sent by the user terminal 101, the voice module 110 sends the received object condition string to the search module 120, and then the search module 120 compares the object condition string with the database 105. The object features in the object are found to match the objects that meet each other within the predetermined condition and the matching objects are sent to the output module 130, and then the output module 130 sends the search result back to the user terminal 101. Preferably, the search module 120 finds objects that conform to each other within predetermined conditions and produces search results that include a particular number of objects, wherein the particular number can be zero or greater than zero.

Please refer to Figure 2 for a schematic diagram of the database of this creation. In Fig. 2, the repository 105 stores the article 106A, for example, a suitable residence and the article 106B is, for example, a certain mansion. For example, the object can be a village, a residential building, a national residence, a condominium, a suitable residence, a social residence, or a specific apartment, a mansion, a residential building, a suite, a translucent or other residence. Type. The object 106A has the object feature A01, for example, the house age is 15 years, the object feature A02 is, for example, 20 households belonging to the object, the object feature A03 is, for example, the living function is the store and the object feature A04 is, for example, a public swimming pool, and the object 106A is further There is a saleable item S01 and a saleable item S02. The object 106B has an object feature A01, for example, a house age of 15 years, an object feature A02, for example, 15 households belonging to the object, and an object feature A03, for example, a living function for the city. Field, wherein the saleable item of object 106B is zero. For example, the object features may be the number of houses, the age of the house, the state of the public, the number of households belonging to the object, the function of the living, the number of floors, the orientation of the house, and the number of floors. Preferably, the repository 105 can store data for one or more items. Preferably, the article may have one or more object features. Preferably, the object has a saleable item that can be zero or greater than zero.

The correspondence between the object 106A and the saleable item S01 and the saleable item S02 needs to be completed by some means, because these correspondences can be queried without public data. Specifically, according to the location of the township, urban area, land section or building area, the total area of land transfer, square meters, urban land use partition, transaction year, transaction number, transfer level, total number of floors , construction type, main use, main building materials, construction completion date, total area of building transfer square meters, construction status, presence or absence of management organization, total price, unit price per square meter or object name, etc., can choose All, or choose a few from them, and construct the object features of most objects, and use this to disassemble the transaction data into multiple fields to provide search comparison. Then, according to the house condition of the saleable item S01 and the saleable item S02, it is intended to compare the address of the house condition, the total number of floors and the completion date of the building with the object features of the plurality of objects in the database, The search obtains at least one specific item information corresponding to the house condition satisfying the saleable item S01 and the saleable item S0, and completes the establishment of the relationship between the item 106A and the saleable item S01 and the saleable item S02.

Continuing to refer to FIG. 1 and FIG. 2, the search module 120 compares the received object condition string with the object features of the plurality of objects 106 in the database 105 to find objects that conform to each other within predetermined conditions, such as The object condition string is 15 years old, and the search module 120 compares the object features in the database 105 to find out that the object feature A01 of the object 106A and the object 106B is 15 years old, so the items satisfying the comparison condition are met. The article is the object 106A and the object 106B, and then the search module 120 sends the object 106A and the object 106B to the output module 130 to generate a search result.

In the present creation, the search module 120 compares within predetermined conditions, and the predetermined condition includes (1) the object condition string is a numerical value, the residential group feature is the same as the object condition string, and the search result shows the object that completely conforms; (2) The object condition string is a numerical value, and the residential group feature is different from the object condition string. The difference range is the range of the object condition string added and subtracted by the predetermined value, and the search result shows that the object is partially matched; (3) the object condition string is The text, the characteristics of the residential group and the object condition string are the same, the search result shows the object that exactly matches the object; and (4) the object condition string is the text, and the residential group feature and the object condition string are different, the search result shows the residential group features and objects The condition string is similar to the part that matches the object. For example, if the object condition string is 20 households belonging to the object, the search module 120 compares the search range of the value 20 with the value of 15 to 25 to compare the object features in the database 105, thereby finding the housing group. The object 106A of the 20 households belonging to the object belonging to the object and the object group 106B of the household belonging to the number of the community belonging to the object are 106B. If the conditional string of the object is the living function as the market, the search module 120 has the characteristics of the residential group. In addition to the item 106B of the market, similar features will be used to find the item 106A with the feature of the house group. Among them, the market, the store, etc. belong to similar conditions and need to complete the induction and build the database in advance.

Please refer to Figure 3 for a schematic diagram of the system search page for this creation. In FIG. 3, the system search page 20 includes search type options 205-206, search conditions 210-211, and search button 215. After the user selects the type option and clicks the search button 215 after entering the search condition, the object condition string is sent to the voice module of the system of the creation. Preferably, the search type option 205 and the search condition 210 are necessary input data, and the search type option 206 and the search condition 211 are non-essential input data. If the user wants to input multiple search data, the system search may be clicked. Find "+" in page 20 to generate a new search type option and search criteria field.

Please refer to Figure 4 for a schematic diagram of the system search page for this creation. In FIG. 4, the system search page 20 further includes a map block 220 and a search result block 230, wherein the map block 220 displays the position of the object of the search result on the map, for example, the object 106A is indicated by the mark 221 and the object 106B. The search result block 230 displays the name of the object of the search result, for example, the object 106A is represented by item 231 and the object 106B is represented by item 232. For example, after the user sends out the object condition string, for example, the voice module of the system from the age of 15 years to the creation system, after the database is compared by the search module, the output module will have the residential group feature A01, for example. The item 106A of the house age of 15 years is, for example, a suitable house and the object 106B is sent back to the system search page 20 by a certain building, for example, the search module will confirm whether the object conforming has an saleable item after finding the matching object. If the object that meets the object does not have a saleable item, it will be included in the non-conforming object and removed from the comparison result, that is, the search result does not present the object that meets the comparison condition but does not have any saleable object data. In the example, the article 106A has the saleable item S01 and the saleable item S02, and the object 106B has the saleable item S01, so that all the items having the saleable item and satisfying the comparison condition are further matched by the search module. The quantity of the saleable item data in the object is ordered by at least more than the object in the search result. For example, the object 106A has more items available for sale than the object 106B, so the object 106A is ranked higher than the object. 106B, whereby the user can know which items meet the search conditions and have the saleable items, and at the same time, the items with more saleable items can be preferentially selected.

Please refer to Figure 5 for a schematic diagram of the system search page for this creation. Figure 5 is a continuation of Figure 4, after the user obtains the preliminary search result and then relates to one of the at least one object feature, the second voice object strip The operation module, and the voice module 110 uses the voice recognition phrase relative to the search context to convert the second voice object condition into a second object condition string according to the search scenario, and then the second object condition string. Re-searching in the preliminary search results. Since the information of the preliminary search results has been stored on the user side, the search will only read the cache of the user and will not re-access the database to reduce The burden of the database.

In more detail, the search module compares at least one object feature of the second object condition string and the preliminary search result that meets the matching condition, and finds at least one residential group feature and the second object condition string are scheduled. The object that meets the conditions in the condition, and generates one of the objects including the matching condition to search for the result. If the search module compares the second object condition string with at least one object feature of the object in the search result that meets the matching condition, And finding an object that at least one of the residential group features and the second object condition string meet each other within the predetermined condition, the search module removes the non-compliant object from the search result and presents the matching object in the re-search result. . For example, the user sends out the second item condition string, for example, a swimming pool, and only the object 106A in the preliminary search result has the housing group feature A04, for example, a public swimming pool, so the system search page 20 is based on the second object condition. The string removes the object 106B from the map block 220 and the search result block 230, leaving only the matching object 106A, which is the re-search result. Preferably, if the search module compares the second object condition string with the object feature in the preliminary search result that meets the comparison condition, it does not find that at least one object feature and the second object condition string match each other within predetermined conditions. For the object, the search result is the same as the preliminary search result.

The present invention has been described with reference to the preferred embodiments and examples, which are intended to be illustrative and not restrictive. It will be understood by those skilled in the art that various combinations and modifications may be made without departing from the spirit and scope of the invention.

Claims (10)

A voice object search system includes: a database configured to store a plurality of objects, wherein each of the objects includes at least one object feature; a voice module configured to receive one of the at least one object feature first a voice object condition, and according to a search scenario, using a phonetic recognition phrase relative to the search context, converting the first voice object condition into a first object condition string; and a search module coupled to the voice mode And the database is configured to compare the first object condition string with the at least one object feature to find the plural number of the at least one object feature and the first object condition string in a predetermined condition An object that produces a search result that includes a specific number of the plurality of objects. The voice object search system of claim 1, wherein the mutual compliance within the predetermined condition means that the first item condition string falls within a difference range of the at least one residential group feature. The voice object search system of claim 2, wherein the mutually matching within the predetermined condition comprises: (1) the first object condition string is a value, the at least one residential group feature and the first The object condition string is the same, the search result shows the object that is completely matched; (2) the first object condition string is a value, and the at least one house group feature is different from the first object condition string, and the difference range is The first object condition string is added or subtracted by a predetermined value range, the search result shows a part of the matching object; (3) the first object condition string is a text, the The lesser one of the residential group features is identical to the first object condition string, the search result shows the object that exactly matches the object; and (4) the first object condition string is the text, the at least one residential group feature and the first object condition If the strings are different, the search result shows that the at least one residential group feature is similar to the first object condition string. The voice object search system of claim 3, wherein the voice module is configured to receive a second voice object condition related to one of the at least one object feature, and use the search relative to the search according to the search context The speech recognition phrase of the situation converts the second speech object condition into a second object condition string. The voice object search system of claim 4, wherein the search module is configured to compare the at least one of the plurality of objects that match the second object condition string with the search result. And the object feature is configured to find the plurality of objects that match at least one of the residential group features and the second object condition string in the predetermined condition, and generate one of the plurality of objects including the matching condition to search for the result, Wherein the search module finds the at least one residential group feature and the second after comparing the second object condition string with the at least one object feature of the plurality of objects in the search result that meets the matching condition. If the object condition string matches the object in the predetermined condition, the search module removes the non-compliant object from the search result and presents the matching object in the re-search result. The voice object search system of claim 5, wherein the reading the second object condition string from the cache data to read the data generated by the first object condition string, There is no need to re-access the data of the database. The voice object search system of claim 5, wherein the database is further configured to store a saleable item data of each object and the search module is configured to match the comparison Comparing the plurality of objects of the condition with the saleable item data, and sorting the search result and the re-sorting according to the quantity of the saleable item data in the plurality of items that meet the comparison condition Search for the multiple objects in the search results. The voice object search system of claim 5, wherein if the plurality of items that meet the comparison condition do not have any of the saleable item data, the search result does not exhibit the matching condition with the re-search result. The plurality of objects. The voice object search system of claim 4, wherein the at least one object feature is selected from the group consisting of a house number, a house age, a public state, a community number of objects, a living function, and a house. A group consisting of the number of pings, a house orientation, a number of house floors, and combinations thereof. The voice object search system of claim 1, wherein the plurality of items are a village, a built house, a national house, a collective settlement, a suitable house, a social house, or an apartment within a specific range. Huaxia, residential buildings, suites, and the sky.